Compare commits
34 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| b5c0d6353b | |||
| 08fde0c707 | |||
| 147a64708d | |||
| b36137bc96 | |||
| f3941a4b3e | |||
| 0cae3b4227 | |||
| 09480a973b | |||
| aa9734587a | |||
| a1dd6d393c | |||
| a53ba4f472 | |||
| 9b4a8321b5 | |||
| db0314a1d1 | |||
| df5fcedecf | |||
| 5061df9876 | |||
| 5fe0a75f78 | |||
| dcf3403261 | |||
| bb79d98027 | |||
| f4b0631178 | |||
| 52f3c074dc | |||
| f67188e3a7 | |||
| 72da883add | |||
| bc278d83a3 | |||
| c586650df4 | |||
| cc78a92ed6 | |||
| 12c35e7cb4 | |||
| a885d10436 | |||
| 41150057d6 | |||
| a522fb2f34 | |||
| ec04757740 | |||
| 432c74b927 | |||
| 8199ba6b43 | |||
| abe15bdd7b | |||
| 4d8af3242b | |||
| 2651e61b2c |
+20
-1
@@ -3,7 +3,7 @@ members = ["optimizer-derive"]
|
||||
|
||||
[package]
|
||||
name = "optimizer"
|
||||
version = "0.5.1"
|
||||
version = "0.7.1"
|
||||
edition = "2024"
|
||||
rust-version = "1.88"
|
||||
license = "MIT"
|
||||
@@ -21,15 +21,34 @@ thiserror = "2"
|
||||
parking_lot = "0.12"
|
||||
tokio = { version = "1", features = ["sync", "rt-multi-thread"], optional = true }
|
||||
optimizer-derive = { version = "0.1.0", path = "optimizer-derive", optional = true }
|
||||
serde = { version = "1", features = ["derive"], optional = true }
|
||||
serde_json = { version = "1", optional = true }
|
||||
tracing = { version = "0.1.29", optional = true }
|
||||
sobol_burley = { version = "0.5", optional = true }
|
||||
nalgebra = { version = "0.33", optional = true }
|
||||
|
||||
[features]
|
||||
default = []
|
||||
async = ["dep:tokio"]
|
||||
derive = ["dep:optimizer-derive"]
|
||||
serde = ["dep:serde", "dep:serde_json"]
|
||||
tracing = ["dep:tracing"]
|
||||
sobol = ["dep:sobol_burley"]
|
||||
cma-es = ["dep:nalgebra"]
|
||||
|
||||
[dev-dependencies]
|
||||
tokio = { version = "1", features = ["rt-multi-thread", "macros", "time"] }
|
||||
optimizer-derive = { version = "0.1.0", path = "optimizer-derive" }
|
||||
serde_json = "1"
|
||||
criterion = { version = "0.8", features = ["html_reports"] }
|
||||
|
||||
[[bench]]
|
||||
name = "samplers"
|
||||
harness = false
|
||||
|
||||
[[bench]]
|
||||
name = "optimization"
|
||||
harness = false
|
||||
|
||||
[[example]]
|
||||
name = "async_api_optimization"
|
||||
|
||||
@@ -0,0 +1,112 @@
|
||||
#[allow(dead_code)]
|
||||
mod test_functions;
|
||||
|
||||
use criterion::{BenchmarkId, Criterion, criterion_group, criterion_main};
|
||||
use optimizer::parameter::Parameter;
|
||||
use optimizer::sampler::random::RandomSampler;
|
||||
use optimizer::sampler::tpe::TpeSampler;
|
||||
use optimizer::{FloatParam, Study};
|
||||
|
||||
fn make_params(dims: usize) -> Vec<FloatParam> {
|
||||
(0..dims)
|
||||
.map(|i| FloatParam::new(-5.0, 5.0).name(format!("x{i}")))
|
||||
.collect()
|
||||
}
|
||||
|
||||
fn bench_tpe_sphere(c: &mut Criterion) {
|
||||
let mut group = c.benchmark_group("tpe_sphere");
|
||||
group.sample_size(10);
|
||||
|
||||
for dims in [2, 10, 50] {
|
||||
let params = make_params(dims);
|
||||
group.bench_with_input(BenchmarkId::new("dims", dims), ¶ms, |b, params| {
|
||||
b.iter(|| {
|
||||
let study = Study::minimize(TpeSampler::builder().seed(42).build().unwrap());
|
||||
study
|
||||
.optimize(100, |trial| {
|
||||
let x: Vec<f64> = params
|
||||
.iter()
|
||||
.map(|p| p.suggest(trial))
|
||||
.collect::<Result<_, _>>()
|
||||
.unwrap();
|
||||
Ok::<_, optimizer::Error>(test_functions::sphere(&x))
|
||||
})
|
||||
.unwrap();
|
||||
});
|
||||
});
|
||||
}
|
||||
group.finish();
|
||||
}
|
||||
|
||||
fn bench_tpe_rosenbrock(c: &mut Criterion) {
|
||||
let mut group = c.benchmark_group("tpe_rosenbrock");
|
||||
group.sample_size(10);
|
||||
|
||||
for dims in [2, 10] {
|
||||
let params = make_params(dims);
|
||||
group.bench_with_input(BenchmarkId::new("dims", dims), ¶ms, |b, params| {
|
||||
b.iter(|| {
|
||||
let study = Study::minimize(TpeSampler::builder().seed(42).build().unwrap());
|
||||
study
|
||||
.optimize(100, |trial| {
|
||||
let x: Vec<f64> = params
|
||||
.iter()
|
||||
.map(|p| p.suggest(trial))
|
||||
.collect::<Result<_, _>>()
|
||||
.unwrap();
|
||||
Ok::<_, optimizer::Error>(test_functions::rosenbrock(&x))
|
||||
})
|
||||
.unwrap();
|
||||
});
|
||||
});
|
||||
}
|
||||
group.finish();
|
||||
}
|
||||
|
||||
fn bench_random_vs_tpe(c: &mut Criterion) {
|
||||
let mut group = c.benchmark_group("random_vs_tpe");
|
||||
group.sample_size(10);
|
||||
let params = make_params(5);
|
||||
|
||||
group.bench_function("random_5d", |b| {
|
||||
b.iter(|| {
|
||||
let study = Study::minimize(RandomSampler::with_seed(42));
|
||||
study
|
||||
.optimize(100, |trial| {
|
||||
let x: Vec<f64> = params
|
||||
.iter()
|
||||
.map(|p| p.suggest(trial))
|
||||
.collect::<Result<_, _>>()
|
||||
.unwrap();
|
||||
Ok::<_, optimizer::Error>(test_functions::sphere(&x))
|
||||
})
|
||||
.unwrap();
|
||||
});
|
||||
});
|
||||
|
||||
group.bench_function("tpe_5d", |b| {
|
||||
b.iter(|| {
|
||||
let study = Study::minimize(TpeSampler::builder().seed(42).build().unwrap());
|
||||
study
|
||||
.optimize(100, |trial| {
|
||||
let x: Vec<f64> = params
|
||||
.iter()
|
||||
.map(|p| p.suggest(trial))
|
||||
.collect::<Result<_, _>>()
|
||||
.unwrap();
|
||||
Ok::<_, optimizer::Error>(test_functions::sphere(&x))
|
||||
})
|
||||
.unwrap();
|
||||
});
|
||||
});
|
||||
|
||||
group.finish();
|
||||
}
|
||||
|
||||
criterion_group!(
|
||||
benches,
|
||||
bench_tpe_sphere,
|
||||
bench_tpe_rosenbrock,
|
||||
bench_random_vs_tpe
|
||||
);
|
||||
criterion_main!(benches);
|
||||
@@ -0,0 +1,118 @@
|
||||
use std::collections::HashMap;
|
||||
|
||||
use criterion::{BenchmarkId, Criterion, criterion_group, criterion_main};
|
||||
use optimizer::parameter::Parameter;
|
||||
use optimizer::sampler::Sampler;
|
||||
use optimizer::sampler::grid::GridSearchSampler;
|
||||
use optimizer::sampler::random::RandomSampler;
|
||||
use optimizer::sampler::tpe::TpeSampler;
|
||||
use optimizer::{CompletedTrial, FloatParam};
|
||||
|
||||
/// Build a synthetic history of `n` completed trials over `dims` float parameters.
|
||||
fn build_history(n: usize, dims: usize) -> Vec<CompletedTrial<f64>> {
|
||||
let params: Vec<FloatParam> = (0..dims)
|
||||
.map(|i| FloatParam::new(-5.0, 5.0).name(format!("x{i}")))
|
||||
.collect();
|
||||
|
||||
let mut history = Vec::with_capacity(n);
|
||||
let sampler = RandomSampler::with_seed(42);
|
||||
|
||||
for trial_id in 0..n {
|
||||
let id = trial_id as u64;
|
||||
let mut param_values = HashMap::new();
|
||||
let mut distributions = HashMap::new();
|
||||
let mut param_labels = HashMap::new();
|
||||
for p in ¶ms {
|
||||
let dist = p.distribution();
|
||||
let val = sampler.sample(&dist, id, &history);
|
||||
param_values.insert(p.id(), val);
|
||||
distributions.insert(p.id(), dist);
|
||||
param_labels.insert(p.id(), p.label());
|
||||
}
|
||||
// Use sphere function value as objective
|
||||
let value: f64 = param_values
|
||||
.values()
|
||||
.map(|v| {
|
||||
let optimizer::ParamValue::Float(f) = v else {
|
||||
unreachable!()
|
||||
};
|
||||
f * f
|
||||
})
|
||||
.sum();
|
||||
history.push(CompletedTrial::new(
|
||||
id,
|
||||
param_values,
|
||||
distributions,
|
||||
param_labels,
|
||||
value,
|
||||
));
|
||||
}
|
||||
history
|
||||
}
|
||||
|
||||
fn bench_tpe_sample(c: &mut Criterion) {
|
||||
let mut group = c.benchmark_group("tpe_sample");
|
||||
let dist = FloatParam::new(-5.0, 5.0).distribution();
|
||||
let tpe = TpeSampler::builder().seed(42).build().unwrap();
|
||||
|
||||
for history_size in [10, 100, 1000] {
|
||||
let history = build_history(history_size, 2);
|
||||
group.bench_with_input(
|
||||
BenchmarkId::new("history", history_size),
|
||||
&history,
|
||||
|b, history| {
|
||||
b.iter(|| tpe.sample(&dist, history.len() as u64, history));
|
||||
},
|
||||
);
|
||||
}
|
||||
group.finish();
|
||||
}
|
||||
|
||||
fn bench_random_sample(c: &mut Criterion) {
|
||||
let mut group = c.benchmark_group("random_sample");
|
||||
let dist = FloatParam::new(-5.0, 5.0).distribution();
|
||||
let sampler = RandomSampler::with_seed(42);
|
||||
|
||||
for history_size in [10, 100, 1000] {
|
||||
let history = build_history(history_size, 2);
|
||||
group.bench_with_input(
|
||||
BenchmarkId::new("history", history_size),
|
||||
&history,
|
||||
|b, history| {
|
||||
b.iter(|| sampler.sample(&dist, history.len() as u64, history));
|
||||
},
|
||||
);
|
||||
}
|
||||
group.finish();
|
||||
}
|
||||
|
||||
fn bench_grid_sample(c: &mut Criterion) {
|
||||
let mut group = c.benchmark_group("grid_sample");
|
||||
let dist = FloatParam::new(-5.0, 5.0).distribution();
|
||||
let history: Vec<CompletedTrial<f64>> = Vec::new();
|
||||
|
||||
for grid_points in [5, 10, 50] {
|
||||
group.bench_with_input(
|
||||
BenchmarkId::new("points", grid_points),
|
||||
&grid_points,
|
||||
|b, _| {
|
||||
b.iter(|| {
|
||||
// Fresh sampler each iteration since grid tracks used points
|
||||
let sampler = GridSearchSampler::builder()
|
||||
.n_points_per_param(grid_points)
|
||||
.build();
|
||||
sampler.sample(&dist, 0, &history)
|
||||
});
|
||||
},
|
||||
);
|
||||
}
|
||||
group.finish();
|
||||
}
|
||||
|
||||
criterion_group!(
|
||||
benches,
|
||||
bench_tpe_sample,
|
||||
bench_random_sample,
|
||||
bench_grid_sample
|
||||
);
|
||||
criterion_main!(benches);
|
||||
@@ -0,0 +1,84 @@
|
||||
//! Standard optimization test functions for benchmarking.
|
||||
|
||||
/// Sphere function: unimodal, convex. Global minimum f(0,...,0) = 0.
|
||||
pub fn sphere(x: &[f64]) -> f64 {
|
||||
x.iter().map(|xi| xi * xi).sum()
|
||||
}
|
||||
|
||||
/// Rosenbrock function: narrow valley. Global minimum f(1,...,1) = 0.
|
||||
pub fn rosenbrock(x: &[f64]) -> f64 {
|
||||
x.windows(2)
|
||||
.map(|w| 100.0 * (w[1] - w[0] * w[0]).powi(2) + (1.0 - w[0]).powi(2))
|
||||
.sum()
|
||||
}
|
||||
|
||||
/// Rastrigin function: highly multimodal. Global minimum f(0,...,0) = 0.
|
||||
pub fn rastrigin(x: &[f64]) -> f64 {
|
||||
let n = x.len() as f64;
|
||||
10.0 * n
|
||||
+ x.iter()
|
||||
.map(|xi| xi * xi - 10.0 * (2.0 * std::f64::consts::PI * xi).cos())
|
||||
.sum::<f64>()
|
||||
}
|
||||
|
||||
/// Ackley function: nearly flat with a deep well. Global minimum f(0,...,0) = 0.
|
||||
pub fn ackley(x: &[f64]) -> f64 {
|
||||
let n = x.len() as f64;
|
||||
let sum_sq: f64 = x.iter().map(|xi| xi * xi).sum();
|
||||
let sum_cos: f64 = x
|
||||
.iter()
|
||||
.map(|xi| (2.0 * std::f64::consts::PI * xi).cos())
|
||||
.sum();
|
||||
-20.0 * (-0.2 * (sum_sq / n).sqrt()).exp() - (sum_cos / n).exp() + 20.0 + std::f64::consts::E
|
||||
}
|
||||
|
||||
/// Branin function (2D only). Three global minima with f* ≈ 0.397887.
|
||||
///
|
||||
/// # Panics
|
||||
///
|
||||
/// Panics if `x` does not have exactly 2 elements.
|
||||
pub fn branin(x: &[f64]) -> f64 {
|
||||
assert!(x.len() == 2, "Branin requires exactly 2 dimensions");
|
||||
let (x1, x2) = (x[0], x[1]);
|
||||
let pi = std::f64::consts::PI;
|
||||
let a = 1.0;
|
||||
let b = 5.1 / (4.0 * pi * pi);
|
||||
let c = 5.0 / pi;
|
||||
let r = 6.0;
|
||||
let s = 10.0;
|
||||
let t = 1.0 / (8.0 * pi);
|
||||
a * (x2 - b * x1 * x1 + c * x1 - r).powi(2) + s * (1.0 - t) * x1.cos() + s
|
||||
}
|
||||
|
||||
/// Hartmann 6D function. Global minimum f* ≈ -3.3224.
|
||||
///
|
||||
/// # Panics
|
||||
///
|
||||
/// Panics if `x` does not have exactly 6 elements.
|
||||
pub fn hartmann6(x: &[f64]) -> f64 {
|
||||
assert!(x.len() == 6, "Hartmann6 requires exactly 6 dimensions");
|
||||
|
||||
let alpha = [1.0, 1.2, 3.0, 3.2];
|
||||
let a_matrix = [
|
||||
[10.0, 3.0, 17.0, 3.5, 1.7, 8.0],
|
||||
[0.05, 10.0, 17.0, 0.1, 8.0, 14.0],
|
||||
[3.0, 3.5, 1.7, 10.0, 17.0, 8.0],
|
||||
[17.0, 8.0, 0.05, 10.0, 0.1, 14.0],
|
||||
];
|
||||
let p_matrix = [
|
||||
[0.1312, 0.1696, 0.5569, 0.0124, 0.8283, 0.5886],
|
||||
[0.2329, 0.4135, 0.8307, 0.3736, 0.1004, 0.9991],
|
||||
[0.2348, 0.1451, 0.3522, 0.2883, 0.3047, 0.6650],
|
||||
[0.4047, 0.8828, 0.8732, 0.5743, 0.1091, 0.0381],
|
||||
];
|
||||
|
||||
let mut result = 0.0;
|
||||
for i in 0..4 {
|
||||
let mut inner = 0.0;
|
||||
for (j, xj) in x.iter().enumerate() {
|
||||
inner += a_matrix[i][j] * (xj - p_matrix[i][j]).powi(2);
|
||||
}
|
||||
result -= alpha[i] * (-inner).exp();
|
||||
}
|
||||
result
|
||||
}
|
||||
@@ -0,0 +1,124 @@
|
||||
use std::ops::ControlFlow;
|
||||
use std::time::Instant;
|
||||
|
||||
use optimizer::parameter::Parameter;
|
||||
use optimizer::sampler::random::RandomSampler;
|
||||
use optimizer::sampler::tpe::TpeSampler;
|
||||
use optimizer::{FloatParam, Study};
|
||||
|
||||
/// Standard optimization test functions.
|
||||
mod functions {
|
||||
pub fn sphere(x: &[f64]) -> f64 {
|
||||
x.iter().map(|xi| xi * xi).sum()
|
||||
}
|
||||
|
||||
pub fn rosenbrock(x: &[f64]) -> f64 {
|
||||
x.windows(2)
|
||||
.map(|w| 100.0 * (w[1] - w[0] * w[0]).powi(2) + (1.0 - w[0]).powi(2))
|
||||
.sum()
|
||||
}
|
||||
|
||||
pub fn rastrigin(x: &[f64]) -> f64 {
|
||||
let n = x.len() as f64;
|
||||
10.0 * n
|
||||
+ x.iter()
|
||||
.map(|xi| xi * xi - 10.0 * (2.0 * std::f64::consts::PI * xi).cos())
|
||||
.sum::<f64>()
|
||||
}
|
||||
}
|
||||
|
||||
fn run_convergence(
|
||||
name: &str,
|
||||
sampler_name: &str,
|
||||
study: Study<f64>,
|
||||
params: &[FloatParam],
|
||||
objective: fn(&[f64]) -> f64,
|
||||
n_trials: usize,
|
||||
) {
|
||||
let start = Instant::now();
|
||||
|
||||
study
|
||||
.optimize_with_callback(
|
||||
n_trials,
|
||||
|trial| {
|
||||
let x: Vec<f64> = params
|
||||
.iter()
|
||||
.map(|p| p.suggest(trial))
|
||||
.collect::<Result<_, _>>()
|
||||
.unwrap();
|
||||
Ok::<_, optimizer::Error>(objective(&x))
|
||||
},
|
||||
|study, _trial| {
|
||||
let elapsed = start.elapsed().as_millis();
|
||||
let best = study.best_value().unwrap();
|
||||
let n = study.n_trials();
|
||||
println!("{n},{best},{elapsed},{sampler_name},{name}");
|
||||
ControlFlow::Continue(())
|
||||
},
|
||||
)
|
||||
.unwrap();
|
||||
}
|
||||
|
||||
fn main() {
|
||||
println!("trial,best_value,elapsed_ms,sampler,function");
|
||||
|
||||
let dims = 5;
|
||||
let params: Vec<FloatParam> = (0..dims)
|
||||
.map(|i| FloatParam::new(-5.0, 5.0).name(format!("x{i}")))
|
||||
.collect();
|
||||
let n_trials = 200;
|
||||
|
||||
// Sphere: Random vs TPE
|
||||
run_convergence(
|
||||
"sphere_5d",
|
||||
"random",
|
||||
Study::minimize(RandomSampler::with_seed(1)),
|
||||
¶ms,
|
||||
functions::sphere,
|
||||
n_trials,
|
||||
);
|
||||
run_convergence(
|
||||
"sphere_5d",
|
||||
"tpe",
|
||||
Study::minimize(TpeSampler::builder().seed(1).build().unwrap()),
|
||||
¶ms,
|
||||
functions::sphere,
|
||||
n_trials,
|
||||
);
|
||||
|
||||
// Rosenbrock: Random vs TPE
|
||||
run_convergence(
|
||||
"rosenbrock_5d",
|
||||
"random",
|
||||
Study::minimize(RandomSampler::with_seed(2)),
|
||||
¶ms,
|
||||
functions::rosenbrock,
|
||||
n_trials,
|
||||
);
|
||||
run_convergence(
|
||||
"rosenbrock_5d",
|
||||
"tpe",
|
||||
Study::minimize(TpeSampler::builder().seed(2).build().unwrap()),
|
||||
¶ms,
|
||||
functions::rosenbrock,
|
||||
n_trials,
|
||||
);
|
||||
|
||||
// Rastrigin: Random vs TPE
|
||||
run_convergence(
|
||||
"rastrigin_5d",
|
||||
"random",
|
||||
Study::minimize(RandomSampler::with_seed(3)),
|
||||
¶ms,
|
||||
functions::rastrigin,
|
||||
n_trials,
|
||||
);
|
||||
run_convergence(
|
||||
"rastrigin_5d",
|
||||
"tpe",
|
||||
Study::minimize(TpeSampler::builder().seed(3).build().unwrap()),
|
||||
¶ms,
|
||||
functions::rastrigin,
|
||||
n_trials,
|
||||
);
|
||||
}
|
||||
@@ -13,4 +13,3 @@ proc-macro = true
|
||||
[dependencies]
|
||||
syn = { version = "2", features = ["full"] }
|
||||
quote = "1"
|
||||
proc-macro2 = "1"
|
||||
|
||||
@@ -2,6 +2,7 @@
|
||||
|
||||
/// Distribution for floating-point parameters.
|
||||
#[derive(Clone, Debug, PartialEq)]
|
||||
#[cfg_attr(feature = "serde", derive(serde::Serialize, serde::Deserialize))]
|
||||
pub struct FloatDistribution {
|
||||
/// Lower bound (inclusive).
|
||||
pub low: f64,
|
||||
@@ -15,6 +16,7 @@ pub struct FloatDistribution {
|
||||
|
||||
/// Distribution for integer parameters.
|
||||
#[derive(Clone, Debug, PartialEq)]
|
||||
#[cfg_attr(feature = "serde", derive(serde::Serialize, serde::Deserialize))]
|
||||
pub struct IntDistribution {
|
||||
/// Lower bound (inclusive).
|
||||
pub low: i64,
|
||||
@@ -28,6 +30,7 @@ pub struct IntDistribution {
|
||||
|
||||
/// Distribution for categorical parameters.
|
||||
#[derive(Clone, Debug, PartialEq)]
|
||||
#[cfg_attr(feature = "serde", derive(serde::Serialize, serde::Deserialize))]
|
||||
pub struct CategoricalDistribution {
|
||||
/// Number of choices available.
|
||||
pub n_choices: usize,
|
||||
@@ -35,6 +38,7 @@ pub struct CategoricalDistribution {
|
||||
|
||||
/// Enum wrapping all parameter distribution types.
|
||||
#[derive(Clone, Debug, PartialEq)]
|
||||
#[cfg_attr(feature = "serde", derive(serde::Serialize, serde::Deserialize))]
|
||||
pub enum Distribution {
|
||||
/// A floating-point distribution.
|
||||
Float(FloatDistribution),
|
||||
|
||||
@@ -72,6 +72,10 @@ pub enum Error {
|
||||
got: usize,
|
||||
},
|
||||
|
||||
/// Returned when a trial is pruned (stopped early by the objective function).
|
||||
#[error("trial was pruned")]
|
||||
TrialPruned,
|
||||
|
||||
/// Returned when an internal invariant is violated.
|
||||
#[error("internal error: {0}")]
|
||||
Internal(&'static str),
|
||||
@@ -83,3 +87,33 @@ pub enum Error {
|
||||
}
|
||||
|
||||
pub type Result<T> = core::result::Result<T, Error>;
|
||||
|
||||
/// Convenience type for signalling a pruned trial from an objective function.
|
||||
///
|
||||
/// Implements `Into<Error>` so it can be used with `?` in objectives that
|
||||
/// return `Result<V, Error>`.
|
||||
///
|
||||
/// # Examples
|
||||
///
|
||||
/// ```
|
||||
/// use optimizer::{Error, TrialPruned};
|
||||
///
|
||||
/// fn objective_that_prunes() -> Result<f64, Error> {
|
||||
/// // ... some computation ...
|
||||
/// Err(TrialPruned)?
|
||||
/// }
|
||||
/// ```
|
||||
#[derive(Debug)]
|
||||
pub struct TrialPruned;
|
||||
|
||||
impl core::fmt::Display for TrialPruned {
|
||||
fn fmt(&self, f: &mut core::fmt::Formatter<'_>) -> core::fmt::Result {
|
||||
write!(f, "trial was pruned")
|
||||
}
|
||||
}
|
||||
|
||||
impl From<TrialPruned> for Error {
|
||||
fn from(_: TrialPruned) -> Self {
|
||||
Error::TrialPruned
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,93 @@
|
||||
//! Parameter importance via Spearman rank correlation.
|
||||
|
||||
/// Assign average ranks to a slice of `f64` values (handles ties).
|
||||
#[allow(clippy::cast_precision_loss, clippy::float_cmp)]
|
||||
pub(crate) fn rank(values: &[f64]) -> Vec<f64> {
|
||||
let n = values.len();
|
||||
let mut indexed: Vec<(usize, f64)> = values.iter().copied().enumerate().collect();
|
||||
indexed.sort_by(|a, b| a.1.partial_cmp(&b.1).unwrap_or(core::cmp::Ordering::Equal));
|
||||
|
||||
let mut ranks = vec![0.0; n];
|
||||
let mut i = 0;
|
||||
while i < n {
|
||||
// Find the run of tied values.
|
||||
let mut j = i + 1;
|
||||
while j < n && indexed[j].1 == indexed[i].1 {
|
||||
j += 1;
|
||||
}
|
||||
// Average rank for the tie group (1-based ranks).
|
||||
let avg = (i + 1..=j).sum::<usize>() as f64 / (j - i) as f64;
|
||||
for item in &indexed[i..j] {
|
||||
ranks[item.0] = avg;
|
||||
}
|
||||
i = j;
|
||||
}
|
||||
ranks
|
||||
}
|
||||
|
||||
/// Pearson correlation coefficient on two equal-length slices.
|
||||
#[allow(clippy::cast_precision_loss)]
|
||||
fn pearson(x: &[f64], y: &[f64]) -> f64 {
|
||||
let n = x.len() as f64;
|
||||
let mean_x = x.iter().sum::<f64>() / n;
|
||||
let mean_y = y.iter().sum::<f64>() / n;
|
||||
|
||||
let mut cov = 0.0;
|
||||
let mut var_x = 0.0;
|
||||
let mut var_y = 0.0;
|
||||
for (xi, yi) in x.iter().zip(y.iter()) {
|
||||
let dx = xi - mean_x;
|
||||
let dy = yi - mean_y;
|
||||
cov += dx * dy;
|
||||
var_x += dx * dx;
|
||||
var_y += dy * dy;
|
||||
}
|
||||
|
||||
let denom = (var_x * var_y).sqrt();
|
||||
if denom == 0.0 { 0.0 } else { cov / denom }
|
||||
}
|
||||
|
||||
/// Spearman rank correlation (Pearson on ranks).
|
||||
pub(crate) fn spearman(x: &[f64], y: &[f64]) -> f64 {
|
||||
pearson(&rank(x), &rank(y))
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn rank_no_ties() {
|
||||
let ranks = rank(&[30.0, 10.0, 20.0]);
|
||||
assert_eq!(ranks, vec![3.0, 1.0, 2.0]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rank_with_ties() {
|
||||
let ranks = rank(&[10.0, 20.0, 20.0, 30.0]);
|
||||
assert_eq!(ranks, vec![1.0, 2.5, 2.5, 4.0]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn perfect_positive_correlation() {
|
||||
let x = vec![1.0, 2.0, 3.0, 4.0, 5.0];
|
||||
let y = vec![2.0, 4.0, 6.0, 8.0, 10.0];
|
||||
let r = spearman(&x, &y);
|
||||
assert!((r - 1.0).abs() < 1e-10);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn perfect_negative_correlation() {
|
||||
let x = vec![1.0, 2.0, 3.0, 4.0, 5.0];
|
||||
let y = vec![10.0, 8.0, 6.0, 4.0, 2.0];
|
||||
let r = spearman(&x, &y);
|
||||
assert!((r + 1.0).abs() < 1e-10);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn zero_variance_returns_zero() {
|
||||
let x = vec![5.0, 5.0, 5.0];
|
||||
let y = vec![1.0, 2.0, 3.0];
|
||||
assert!(spearman(&x, &y).abs() < f64::EPSILON);
|
||||
}
|
||||
}
|
||||
+59
-4
@@ -17,6 +17,9 @@
|
||||
//! - **Random Search** - Simple random sampling for baseline comparisons
|
||||
//! - **TPE (Tree-Parzen Estimator)** - Bayesian optimization for efficient search
|
||||
//! - **Grid Search** - Exhaustive search over a specified parameter grid
|
||||
//! - **Sobol (QMC)** - Quasi-random sampling for better space coverage (requires `sobol` feature)
|
||||
//! - **CMA-ES** - Covariance Matrix Adaptation Evolution Strategy for continuous optimization (requires `cma-es` feature)
|
||||
//! - **BOHB** - Bayesian Optimization + `HyperBand` for budget-aware TPE sampling
|
||||
//!
|
||||
//! Additional features include:
|
||||
//!
|
||||
@@ -182,30 +185,71 @@
|
||||
//!
|
||||
//! - `async`: Enable async optimization methods (requires tokio)
|
||||
//! - `derive`: Enable `#[derive(Categorical)]` for enum parameters
|
||||
//! - `serde`: Enable `Serialize`/`Deserialize` on public types and `Study::save()`/`Study::load()`
|
||||
//! - `sobol`: Enable the Sobol quasi-random sampler for better space coverage
|
||||
//! - `cma-es`: Enable the CMA-ES sampler for continuous optimization
|
||||
//! - `tracing`: Emit structured log events via the [`tracing`](https://docs.rs/tracing) crate at key optimization points
|
||||
|
||||
/// Emit a `tracing::info!` event when the `tracing` feature is enabled.
|
||||
/// No-op otherwise.
|
||||
#[cfg(feature = "tracing")]
|
||||
macro_rules! trace_info {
|
||||
($($arg:tt)*) => { tracing::info!($($arg)*) };
|
||||
}
|
||||
|
||||
#[cfg(not(feature = "tracing"))]
|
||||
macro_rules! trace_info {
|
||||
($($arg:tt)*) => {};
|
||||
}
|
||||
|
||||
/// Emit a `tracing::debug!` event when the `tracing` feature is enabled.
|
||||
/// No-op otherwise.
|
||||
#[cfg(feature = "tracing")]
|
||||
macro_rules! trace_debug {
|
||||
($($arg:tt)*) => { tracing::debug!($($arg)*) };
|
||||
}
|
||||
|
||||
#[cfg(not(feature = "tracing"))]
|
||||
macro_rules! trace_debug {
|
||||
($($arg:tt)*) => {};
|
||||
}
|
||||
|
||||
mod distribution;
|
||||
mod error;
|
||||
mod importance;
|
||||
mod kde;
|
||||
mod param;
|
||||
pub mod parameter;
|
||||
pub mod pruner;
|
||||
pub mod sampler;
|
||||
mod study;
|
||||
mod trial;
|
||||
mod types;
|
||||
|
||||
pub use error::{Error, Result};
|
||||
pub use error::{Error, Result, TrialPruned};
|
||||
#[cfg(feature = "derive")]
|
||||
pub use optimizer_derive::Categorical;
|
||||
pub use param::ParamValue;
|
||||
pub use parameter::{
|
||||
BoolParam, Categorical, CategoricalParam, EnumParam, FloatParam, IntParam, ParamId, Parameter,
|
||||
};
|
||||
pub use pruner::{
|
||||
HyperbandPruner, MedianPruner, NopPruner, PatientPruner, PercentilePruner, Pruner,
|
||||
SuccessiveHalvingPruner, ThresholdPruner, WilcoxonPruner,
|
||||
};
|
||||
pub use sampler::CompletedTrial;
|
||||
pub use sampler::bohb::BohbSampler;
|
||||
#[cfg(feature = "cma-es")]
|
||||
pub use sampler::cma_es::CmaEsSampler;
|
||||
pub use sampler::grid::GridSearchSampler;
|
||||
pub use sampler::random::RandomSampler;
|
||||
#[cfg(feature = "sobol")]
|
||||
pub use sampler::sobol::SobolSampler;
|
||||
pub use sampler::tpe::TpeSampler;
|
||||
pub use study::Study;
|
||||
pub use trial::Trial;
|
||||
#[cfg(feature = "serde")]
|
||||
pub use study::StudySnapshot;
|
||||
pub use trial::{AttrValue, Trial};
|
||||
pub use types::{Direction, TrialState};
|
||||
|
||||
/// Convenient wildcard import for the most common types.
|
||||
@@ -217,16 +261,27 @@ pub mod prelude {
|
||||
#[cfg(feature = "derive")]
|
||||
pub use optimizer_derive::Categorical as DeriveCategory;
|
||||
|
||||
pub use crate::error::{Error, Result};
|
||||
pub use crate::error::{Error, Result, TrialPruned};
|
||||
pub use crate::param::ParamValue;
|
||||
pub use crate::parameter::{
|
||||
BoolParam, Categorical, CategoricalParam, EnumParam, FloatParam, IntParam, Parameter,
|
||||
};
|
||||
pub use crate::pruner::{
|
||||
HyperbandPruner, MedianPruner, NopPruner, PatientPruner, PercentilePruner, Pruner,
|
||||
SuccessiveHalvingPruner, ThresholdPruner,
|
||||
};
|
||||
pub use crate::sampler::CompletedTrial;
|
||||
pub use crate::sampler::bohb::BohbSampler;
|
||||
#[cfg(feature = "cma-es")]
|
||||
pub use crate::sampler::cma_es::CmaEsSampler;
|
||||
pub use crate::sampler::grid::GridSearchSampler;
|
||||
pub use crate::sampler::random::RandomSampler;
|
||||
#[cfg(feature = "sobol")]
|
||||
pub use crate::sampler::sobol::SobolSampler;
|
||||
pub use crate::sampler::tpe::TpeSampler;
|
||||
pub use crate::study::Study;
|
||||
pub use crate::trial::Trial;
|
||||
#[cfg(feature = "serde")]
|
||||
pub use crate::study::StudySnapshot;
|
||||
pub use crate::trial::{AttrValue, Trial};
|
||||
pub use crate::types::Direction;
|
||||
}
|
||||
|
||||
@@ -6,6 +6,7 @@
|
||||
/// For categorical parameters, the `Categorical` variant stores
|
||||
/// the index into the choices array.
|
||||
#[derive(Clone, Debug, PartialEq)]
|
||||
#[cfg_attr(feature = "serde", derive(serde::Serialize, serde::Deserialize))]
|
||||
pub enum ParamValue {
|
||||
/// A floating-point parameter value.
|
||||
Float(f64),
|
||||
|
||||
+45
-1
@@ -21,6 +21,7 @@
|
||||
//! ```
|
||||
|
||||
use core::fmt::Debug;
|
||||
use core::ops::RangeInclusive;
|
||||
use core::sync::atomic::{AtomicU64, Ordering};
|
||||
|
||||
use crate::distribution::{
|
||||
@@ -36,7 +37,8 @@ static NEXT_PARAM_ID: AtomicU64 = AtomicU64::new(0);
|
||||
///
|
||||
/// Each parameter is assigned a unique `ParamId` at creation time. Cloning a parameter
|
||||
/// copies its `ParamId`, so clones refer to the same logical parameter.
|
||||
#[derive(Clone, Copy, Debug, PartialEq, Eq, Hash)]
|
||||
#[derive(Clone, Copy, Debug, PartialEq, Eq, PartialOrd, Ord, Hash)]
|
||||
#[cfg_attr(feature = "serde", derive(serde::Serialize, serde::Deserialize))]
|
||||
pub struct ParamId(u64);
|
||||
|
||||
impl ParamId {
|
||||
@@ -187,6 +189,12 @@ impl FloatParam {
|
||||
}
|
||||
}
|
||||
|
||||
impl From<RangeInclusive<f64>> for FloatParam {
|
||||
fn from(range: RangeInclusive<f64>) -> Self {
|
||||
FloatParam::new(*range.start(), *range.end())
|
||||
}
|
||||
}
|
||||
|
||||
impl Parameter for FloatParam {
|
||||
type Value = f64;
|
||||
|
||||
@@ -306,6 +314,12 @@ impl IntParam {
|
||||
}
|
||||
}
|
||||
|
||||
impl From<RangeInclusive<i64>> for IntParam {
|
||||
fn from(range: RangeInclusive<i64>) -> Self {
|
||||
IntParam::new(*range.start(), *range.end())
|
||||
}
|
||||
}
|
||||
|
||||
impl Parameter for IntParam {
|
||||
type Value = i64;
|
||||
|
||||
@@ -992,4 +1006,34 @@ mod tests {
|
||||
let cloned = param.clone();
|
||||
assert_eq!(param.id(), cloned.id());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn float_param_from_range() {
|
||||
let param = FloatParam::from(0.0..=1.0);
|
||||
assert_eq!(
|
||||
param.distribution(),
|
||||
Distribution::Float(FloatDistribution {
|
||||
low: 0.0,
|
||||
high: 1.0,
|
||||
log_scale: false,
|
||||
step: None,
|
||||
})
|
||||
);
|
||||
assert_eq!(param.label(), format!("{param:?}"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn int_param_from_range() {
|
||||
let param = IntParam::from(1..=10);
|
||||
assert_eq!(
|
||||
param.distribution(),
|
||||
Distribution::Int(IntDistribution {
|
||||
low: 1,
|
||||
high: 10,
|
||||
log_scale: false,
|
||||
step: None,
|
||||
})
|
||||
);
|
||||
assert_eq!(param.label(), format!("{param:?}"));
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,559 @@
|
||||
use core::sync::atomic::{AtomicU64, Ordering};
|
||||
use std::collections::HashMap;
|
||||
use std::sync::Mutex;
|
||||
|
||||
use super::Pruner;
|
||||
use crate::sampler::CompletedTrial;
|
||||
use crate::types::{Direction, TrialState};
|
||||
|
||||
/// Hyperband pruner that manages multiple Successive Halving brackets.
|
||||
///
|
||||
/// Hyperband addresses SHA's sensitivity to the `min_resource` choice by
|
||||
/// running multiple brackets, each with a different tradeoff between the
|
||||
/// number of configurations and the starting budget:
|
||||
///
|
||||
/// - Bracket 0: many trials, very small starting budget (aggressive pruning)
|
||||
/// - Bracket 1: fewer trials, larger starting budget (moderate pruning)
|
||||
/// - ...
|
||||
/// - Bracket `s_max`: few trials, full budget (no pruning)
|
||||
///
|
||||
/// Trials are assigned to brackets in round-robin fashion. Each bracket
|
||||
/// runs SHA with its own `min_resource` and rung schedule.
|
||||
///
|
||||
/// # Examples
|
||||
///
|
||||
/// ```
|
||||
/// use optimizer::Direction;
|
||||
/// use optimizer::pruner::HyperbandPruner;
|
||||
///
|
||||
/// let pruner = HyperbandPruner::new()
|
||||
/// .min_resource(1)
|
||||
/// .max_resource(81)
|
||||
/// .reduction_factor(3)
|
||||
/// .direction(Direction::Minimize);
|
||||
/// ```
|
||||
pub struct HyperbandPruner {
|
||||
min_resource: u64,
|
||||
max_resource: u64,
|
||||
reduction_factor: u64,
|
||||
direction: Direction,
|
||||
/// Tracks which bracket each trial belongs to.
|
||||
trial_brackets: Mutex<HashMap<u64, usize>>,
|
||||
/// Counter for round-robin bracket assignment.
|
||||
next_bracket: AtomicU64,
|
||||
}
|
||||
|
||||
impl HyperbandPruner {
|
||||
/// Create a new `HyperbandPruner` with default parameters.
|
||||
///
|
||||
/// Defaults: `min_resource=1`, `max_resource=81`, `reduction_factor=3`,
|
||||
/// `direction=Minimize`.
|
||||
#[must_use]
|
||||
pub fn new() -> Self {
|
||||
Self {
|
||||
min_resource: 1,
|
||||
max_resource: 81,
|
||||
reduction_factor: 3,
|
||||
direction: Direction::Minimize,
|
||||
trial_brackets: Mutex::new(HashMap::new()),
|
||||
next_bracket: AtomicU64::new(0),
|
||||
}
|
||||
}
|
||||
|
||||
/// Set the minimum resource (budget) per trial.
|
||||
///
|
||||
/// # Panics
|
||||
///
|
||||
/// Panics if `r` is 0.
|
||||
#[must_use]
|
||||
pub fn min_resource(mut self, r: u64) -> Self {
|
||||
assert!(r > 0, "min_resource must be > 0, got {r}");
|
||||
self.min_resource = r;
|
||||
self
|
||||
}
|
||||
|
||||
/// Set the maximum resource (budget) per trial.
|
||||
///
|
||||
/// # Panics
|
||||
///
|
||||
/// Panics if `r` is 0.
|
||||
#[must_use]
|
||||
pub fn max_resource(mut self, r: u64) -> Self {
|
||||
assert!(r > 0, "max_resource must be > 0, got {r}");
|
||||
self.max_resource = r;
|
||||
self
|
||||
}
|
||||
|
||||
/// Set the reduction factor (eta). At each rung, the top 1/eta trials survive.
|
||||
///
|
||||
/// # Panics
|
||||
///
|
||||
/// Panics if `eta` is less than 2.
|
||||
#[must_use]
|
||||
pub fn reduction_factor(mut self, eta: u64) -> Self {
|
||||
assert!(eta >= 2, "reduction_factor must be >= 2, got {eta}");
|
||||
self.reduction_factor = eta;
|
||||
self
|
||||
}
|
||||
|
||||
/// Set the optimization direction.
|
||||
#[must_use]
|
||||
pub fn direction(mut self, d: Direction) -> Self {
|
||||
self.direction = d;
|
||||
self
|
||||
}
|
||||
|
||||
/// Compute `s_max = floor(log(max_resource / min_resource) / log(eta))`.
|
||||
#[allow(
|
||||
clippy::cast_precision_loss,
|
||||
clippy::cast_possible_truncation,
|
||||
clippy::cast_sign_loss
|
||||
)]
|
||||
fn s_max(&self) -> u64 {
|
||||
let eta = self.reduction_factor as f64;
|
||||
let ratio = self.max_resource as f64 / self.min_resource as f64;
|
||||
(ratio.ln() / eta.ln()).floor() as u64
|
||||
}
|
||||
|
||||
/// Compute the rung steps for a given bracket `s`.
|
||||
///
|
||||
/// For bracket `s`, the starting resource is `max_resource / eta^(s_max - s)`,
|
||||
/// and rungs are spaced at powers of eta from there up to `max_resource`.
|
||||
#[allow(
|
||||
clippy::cast_precision_loss,
|
||||
clippy::cast_possible_truncation,
|
||||
clippy::cast_sign_loss
|
||||
)]
|
||||
fn rung_steps_for_bracket(&self, bracket: usize) -> Vec<u64> {
|
||||
let s_max = self.s_max();
|
||||
let eta = self.reduction_factor as f64;
|
||||
|
||||
// Starting resource for this bracket
|
||||
let exponent = s_max.saturating_sub(bracket as u64);
|
||||
let min_resource_bracket =
|
||||
(self.max_resource as f64 / eta.powi(exponent as i32)).ceil() as u64;
|
||||
|
||||
let mut steps = Vec::new();
|
||||
let mut rung: u32 = 0;
|
||||
while let Some(power) = self.reduction_factor.checked_pow(rung) {
|
||||
let step = min_resource_bracket.saturating_mul(power);
|
||||
if step > self.max_resource {
|
||||
break;
|
||||
}
|
||||
steps.push(step);
|
||||
rung += 1;
|
||||
}
|
||||
steps
|
||||
}
|
||||
|
||||
/// Assign a trial to a bracket (round-robin) and return the bracket index.
|
||||
#[allow(clippy::cast_possible_truncation)]
|
||||
fn assign_bracket(&self, trial_id: u64) -> usize {
|
||||
let n_brackets = (self.s_max() + 1) as usize;
|
||||
let mut map = self.trial_brackets.lock().expect("lock poisoned");
|
||||
*map.entry(trial_id).or_insert_with(|| {
|
||||
let idx = self.next_bracket.fetch_add(1, Ordering::Relaxed);
|
||||
(idx as usize) % n_brackets
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
impl Default for HyperbandPruner {
|
||||
fn default() -> Self {
|
||||
Self::new()
|
||||
}
|
||||
}
|
||||
|
||||
#[allow(clippy::cast_precision_loss)]
|
||||
impl Pruner for HyperbandPruner {
|
||||
fn should_prune(
|
||||
&self,
|
||||
trial_id: u64,
|
||||
step: u64,
|
||||
intermediate_values: &[(u64, f64)],
|
||||
completed_trials: &[CompletedTrial],
|
||||
) -> bool {
|
||||
let bracket = self.assign_bracket(trial_id);
|
||||
let rungs = self.rung_steps_for_bracket(bracket);
|
||||
|
||||
// Find the highest rung step <= current step
|
||||
let Some(&rung_step) = rungs.iter().rev().find(|&&r| r <= step) else {
|
||||
return false;
|
||||
};
|
||||
|
||||
// Never prune at the last rung (full budget)
|
||||
if rung_step >= self.max_resource {
|
||||
return false;
|
||||
}
|
||||
|
||||
// Get the current trial's value at this rung step
|
||||
let current_value =
|
||||
if let Some(&(_, v)) = intermediate_values.iter().find(|(s, _)| *s == rung_step) {
|
||||
v
|
||||
} else if let Some(&(_, v)) = intermediate_values
|
||||
.iter()
|
||||
.rev()
|
||||
.find(|(s, _)| *s <= rung_step)
|
||||
{
|
||||
v
|
||||
} else {
|
||||
return false;
|
||||
};
|
||||
|
||||
self.is_pruned_at_rung(current_value, rung_step, bracket, completed_trials)
|
||||
}
|
||||
}
|
||||
|
||||
impl HyperbandPruner {
|
||||
/// Determine whether a trial should be pruned at the given rung within its bracket.
|
||||
///
|
||||
/// Only compares against other trials in the same bracket.
|
||||
#[allow(
|
||||
clippy::cast_precision_loss,
|
||||
clippy::cast_possible_truncation,
|
||||
clippy::cast_sign_loss
|
||||
)]
|
||||
fn is_pruned_at_rung(
|
||||
&self,
|
||||
current_value: f64,
|
||||
rung_step: u64,
|
||||
bracket: usize,
|
||||
completed_trials: &[CompletedTrial],
|
||||
) -> bool {
|
||||
let eta = self.reduction_factor as usize;
|
||||
|
||||
// Collect values at this rung step from trials in the same bracket
|
||||
let map = self.trial_brackets.lock().expect("lock poisoned");
|
||||
let mut values_at_rung: Vec<f64> = completed_trials
|
||||
.iter()
|
||||
.filter(|t| t.state == TrialState::Complete || t.state == TrialState::Pruned)
|
||||
.filter(|t| map.get(&t.id).copied() == Some(bracket))
|
||||
.filter_map(|t| {
|
||||
t.intermediate_values
|
||||
.iter()
|
||||
.find(|(s, _)| *s == rung_step)
|
||||
.map(|(_, v)| *v)
|
||||
})
|
||||
.collect();
|
||||
drop(map);
|
||||
|
||||
// Need at least eta trials to make a meaningful comparison
|
||||
if values_at_rung.len() < eta {
|
||||
return false;
|
||||
}
|
||||
|
||||
values_at_rung.push(current_value);
|
||||
|
||||
values_at_rung
|
||||
.sort_unstable_by(|a, b| a.partial_cmp(b).unwrap_or(core::cmp::Ordering::Equal));
|
||||
if self.direction == Direction::Maximize {
|
||||
values_at_rung.reverse();
|
||||
}
|
||||
|
||||
let n_keep = (values_at_rung.len() as f64 / eta as f64).ceil() as usize;
|
||||
let threshold_idx = n_keep.max(1) - 1;
|
||||
let threshold = values_at_rung[threshold_idx];
|
||||
|
||||
match self.direction {
|
||||
Direction::Minimize => current_value > threshold,
|
||||
Direction::Maximize => current_value < threshold,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
#[allow(clippy::cast_precision_loss)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
fn make_trial(id: u64, values: &[(u64, f64)]) -> CompletedTrial {
|
||||
use std::collections::HashMap;
|
||||
|
||||
use crate::parameter::ParamId;
|
||||
|
||||
CompletedTrial::with_intermediate_values(
|
||||
id,
|
||||
HashMap::<ParamId, crate::ParamValue>::new(),
|
||||
HashMap::new(),
|
||||
HashMap::new(),
|
||||
0.0,
|
||||
values.to_vec(),
|
||||
HashMap::new(),
|
||||
)
|
||||
}
|
||||
|
||||
fn make_pruned_trial(id: u64, values: &[(u64, f64)]) -> CompletedTrial {
|
||||
let mut t = make_trial(id, values);
|
||||
t.state = TrialState::Pruned;
|
||||
t
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn s_max_default() {
|
||||
let pruner = HyperbandPruner::new();
|
||||
// s_max = floor(ln(81/1) / ln(3)) = floor(4.0) = 4
|
||||
assert_eq!(pruner.s_max(), 4);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn s_max_custom() {
|
||||
let pruner = HyperbandPruner::new()
|
||||
.min_resource(1)
|
||||
.max_resource(16)
|
||||
.reduction_factor(2);
|
||||
// s_max = floor(ln(16) / ln(2)) = floor(4.0) = 4
|
||||
assert_eq!(pruner.s_max(), 4);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn bracket_count() {
|
||||
let pruner = HyperbandPruner::new();
|
||||
// s_max=4, so brackets 0..=4 → 5 brackets
|
||||
assert_eq!(pruner.s_max() + 1, 5);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rung_steps_bracket_0_default() {
|
||||
let pruner = HyperbandPruner::new();
|
||||
// Bracket 0: min_resource_bracket = ceil(81 / 3^4) = ceil(81/81) = 1
|
||||
// Rungs: 1, 3, 9, 27, 81
|
||||
assert_eq!(pruner.rung_steps_for_bracket(0), vec![1, 3, 9, 27, 81]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rung_steps_bracket_2_default() {
|
||||
let pruner = HyperbandPruner::new();
|
||||
// Bracket 2: min_resource_bracket = ceil(81 / 3^(4-2)) = ceil(81/9) = 9
|
||||
// Rungs: 9, 27, 81
|
||||
assert_eq!(pruner.rung_steps_for_bracket(2), vec![9, 27, 81]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rung_steps_bracket_4_default() {
|
||||
let pruner = HyperbandPruner::new();
|
||||
// Bracket 4 (s_max): min_resource_bracket = ceil(81 / 3^0) = 81
|
||||
// Rungs: 81 only (no pruning, full budget)
|
||||
assert_eq!(pruner.rung_steps_for_bracket(4), vec![81]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rung_steps_eta2() {
|
||||
let pruner = HyperbandPruner::new()
|
||||
.min_resource(1)
|
||||
.max_resource(16)
|
||||
.reduction_factor(2);
|
||||
// s_max = 4
|
||||
// Bracket 0: min=ceil(16/2^4)=1, rungs: 1,2,4,8,16
|
||||
assert_eq!(pruner.rung_steps_for_bracket(0), vec![1, 2, 4, 8, 16]);
|
||||
// Bracket 2: min=ceil(16/2^2)=4, rungs: 4,8,16
|
||||
assert_eq!(pruner.rung_steps_for_bracket(2), vec![4, 8, 16]);
|
||||
// Bracket 4: min=16, rungs: 16
|
||||
assert_eq!(pruner.rung_steps_for_bracket(4), vec![16]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn round_robin_bracket_assignment() {
|
||||
let pruner = HyperbandPruner::new(); // 5 brackets (0..=4)
|
||||
// Trials get assigned in round-robin: 0→0, 1→1, 2→2, 3→3, 4→4, 5→0, ...
|
||||
assert_eq!(pruner.assign_bracket(100), 0);
|
||||
assert_eq!(pruner.assign_bracket(101), 1);
|
||||
assert_eq!(pruner.assign_bracket(102), 2);
|
||||
assert_eq!(pruner.assign_bracket(103), 3);
|
||||
assert_eq!(pruner.assign_bracket(104), 4);
|
||||
assert_eq!(pruner.assign_bracket(105), 0); // wraps around
|
||||
|
||||
// Repeated calls for same trial return same bracket
|
||||
assert_eq!(pruner.assign_bracket(100), 0);
|
||||
assert_eq!(pruner.assign_bracket(103), 3);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn no_prune_before_first_rung() {
|
||||
let pruner = HyperbandPruner::new().direction(Direction::Minimize);
|
||||
// Assign trial 0 to bracket 0 (rungs: 1, 3, 9, 27, 81)
|
||||
pruner.assign_bracket(0);
|
||||
|
||||
// Register completed trials in bracket 0
|
||||
let mut completed = Vec::new();
|
||||
for i in 1..=9 {
|
||||
pruner.assign_bracket(i);
|
||||
completed.push(make_trial(i, &[(1, i as f64)]));
|
||||
}
|
||||
|
||||
// Trial at step 0 (before rung 1) → don't prune
|
||||
assert!(!pruner.should_prune(0, 0, &[(0, 100.0)], &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn no_prune_at_max_resource() {
|
||||
let pruner = HyperbandPruner::new().direction(Direction::Minimize);
|
||||
|
||||
// Put all trials in bracket 0
|
||||
let mut completed = Vec::new();
|
||||
for i in 0..9 {
|
||||
pruner.assign_bracket(i);
|
||||
completed.push(make_trial(i, &[(81, (i + 1) as f64)]));
|
||||
}
|
||||
|
||||
let trial_id = 9;
|
||||
pruner.assign_bracket(trial_id);
|
||||
// At max_resource (81), never prune
|
||||
assert!(!pruner.should_prune(trial_id, 81, &[(81, 100.0)], &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn prune_worst_in_bracket_minimize() {
|
||||
let pruner = HyperbandPruner::new().direction(Direction::Minimize);
|
||||
|
||||
// Force all trials into bracket 0 by assigning sequentially
|
||||
// With 5 brackets, trials 0,5,10,... go to bracket 0
|
||||
let bracket_0_ids: Vec<u64> = (0..5).map(|i| i * 5).collect();
|
||||
// Assign all 25 trial IDs to fill brackets
|
||||
for i in 0..25 {
|
||||
pruner.assign_bracket(i);
|
||||
}
|
||||
|
||||
// Create 9 completed trials in bracket 0 at rung step=1
|
||||
let completed: Vec<_> = bracket_0_ids
|
||||
.iter()
|
||||
.take(3)
|
||||
.enumerate()
|
||||
.map(|(idx, &id)| make_trial(id, &[(1, (idx + 1) as f64)]))
|
||||
.collect();
|
||||
|
||||
// Trial 25 → bracket 0 (25 % 5 == 0)
|
||||
let test_id = 25;
|
||||
pruner.assign_bracket(test_id);
|
||||
assert_eq!(pruner.assign_bracket(test_id), 0);
|
||||
|
||||
// 3 completed + 1 current = 4. eta=3. ceil(4/3)=2. Threshold = 2.0
|
||||
// Value 2.0 → keep
|
||||
assert!(!pruner.should_prune(test_id, 1, &[(1, 2.0)], &completed));
|
||||
// Value 3.0 → prune
|
||||
assert!(pruner.should_prune(test_id, 1, &[(1, 3.0)], &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn prune_worst_in_bracket_maximize() {
|
||||
let pruner = HyperbandPruner::new().direction(Direction::Maximize);
|
||||
|
||||
// Assign trials so they end up in bracket 0
|
||||
for i in 0..25 {
|
||||
pruner.assign_bracket(i);
|
||||
}
|
||||
|
||||
let completed: Vec<_> = [0u64, 5, 10]
|
||||
.iter()
|
||||
.enumerate()
|
||||
.map(|(idx, &id)| make_trial(id, &[(1, (idx + 1) as f64)]))
|
||||
.collect();
|
||||
|
||||
let test_id = 25;
|
||||
pruner.assign_bracket(test_id);
|
||||
|
||||
// For maximize, best = highest. Values: 1,2,3 + current
|
||||
// Value 2.0 → keep (threshold = 2.0 when sorted desc: 3,2,current,1)
|
||||
assert!(!pruner.should_prune(test_id, 1, &[(1, 2.0)], &completed));
|
||||
// Value 1.0 → prune
|
||||
assert!(pruner.should_prune(test_id, 1, &[(1, 0.5)], &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn different_brackets_have_different_aggressiveness() {
|
||||
let pruner = HyperbandPruner::new()
|
||||
.min_resource(1)
|
||||
.max_resource(81)
|
||||
.reduction_factor(3)
|
||||
.direction(Direction::Minimize);
|
||||
|
||||
let rungs_0 = pruner.rung_steps_for_bracket(0);
|
||||
let rungs_2 = pruner.rung_steps_for_bracket(2);
|
||||
let rungs_4 = pruner.rung_steps_for_bracket(4);
|
||||
|
||||
// Bracket 0 has the most rungs (most aggressive)
|
||||
assert!(rungs_0.len() > rungs_2.len());
|
||||
// Bracket 4 has just 1 rung (no pruning)
|
||||
assert_eq!(rungs_4.len(), 1);
|
||||
// Bracket 0 starts earliest
|
||||
assert!(rungs_0[0] < rungs_2[0]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn trials_in_different_brackets_independent() {
|
||||
let pruner = HyperbandPruner::new().direction(Direction::Minimize);
|
||||
|
||||
// Assign trials: bracket 0 gets IDs 0,5,10,15,20
|
||||
for i in 0..25 {
|
||||
pruner.assign_bracket(i);
|
||||
}
|
||||
|
||||
// Bracket 0 trials: bad values at rung step=1
|
||||
let bracket_0_trials: Vec<_> = [0u64, 5, 10]
|
||||
.iter()
|
||||
.map(|&id| make_trial(id, &[(1, 100.0)]))
|
||||
.collect();
|
||||
|
||||
// Bracket 1 trials: good values at rung step=1
|
||||
let bracket_1_trials: Vec<_> = [1u64, 6, 11]
|
||||
.iter()
|
||||
.map(|&id| make_trial(id, &[(1, 1.0)]))
|
||||
.collect();
|
||||
|
||||
let mut all_trials = bracket_0_trials;
|
||||
all_trials.extend(bracket_1_trials);
|
||||
|
||||
// A new bracket-0 trial with value 50 should be compared against
|
||||
// bracket-0 peers (100,100,100), not bracket-1 peers (1,1,1)
|
||||
let test_id = 25; // bracket 0
|
||||
pruner.assign_bracket(test_id);
|
||||
// 3 peers at 100.0 + current at 50.0. ceil(4/3)=2. Sorted: 50,100,100,100. Threshold=100.0
|
||||
// Value 50.0 < 100.0 → keep
|
||||
assert!(!pruner.should_prune(test_id, 1, &[(1, 50.0)], &all_trials));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn includes_pruned_trials() {
|
||||
let pruner = HyperbandPruner::new().direction(Direction::Minimize);
|
||||
|
||||
for i in 0..25 {
|
||||
pruner.assign_bracket(i);
|
||||
}
|
||||
|
||||
let completed = vec![
|
||||
make_trial(0, &[(1, 1.0)]),
|
||||
make_pruned_trial(5, &[(1, 8.0)]),
|
||||
make_pruned_trial(10, &[(1, 9.0)]),
|
||||
];
|
||||
|
||||
let test_id = 25;
|
||||
pruner.assign_bracket(test_id);
|
||||
|
||||
// Values: 1.0, 8.0, 9.0 + current. eta=3.
|
||||
// Value 1.0 → keep
|
||||
assert!(!pruner.should_prune(test_id, 1, &[(1, 1.0)], &completed));
|
||||
// Value 5.0 → prune (sorted: 1,5,8,9 → keep ceil(4/3)=2 → threshold=5.0, 5.0 not > 5.0 → keep)
|
||||
assert!(!pruner.should_prune(test_id, 1, &[(1, 5.0)], &completed));
|
||||
// Value 6.0 → prune (sorted: 1,6,8,9 → threshold=6.0, 6.0 not > 6.0 → keep)
|
||||
assert!(!pruner.should_prune(test_id, 1, &[(1, 6.0)], &completed));
|
||||
// Value 9.5 → prune
|
||||
assert!(pruner.should_prune(test_id, 1, &[(1, 9.5)], &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
#[should_panic(expected = "min_resource must be > 0")]
|
||||
fn rejects_zero_min_resource() {
|
||||
let _ = HyperbandPruner::new().min_resource(0);
|
||||
}
|
||||
|
||||
#[test]
|
||||
#[should_panic(expected = "max_resource must be > 0")]
|
||||
fn rejects_zero_max_resource() {
|
||||
let _ = HyperbandPruner::new().max_resource(0);
|
||||
}
|
||||
|
||||
#[test]
|
||||
#[should_panic(expected = "reduction_factor must be >= 2")]
|
||||
fn rejects_reduction_factor_one() {
|
||||
let _ = HyperbandPruner::new().reduction_factor(1);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,127 @@
|
||||
use super::Pruner;
|
||||
use super::percentile::compute_percentile;
|
||||
use crate::sampler::CompletedTrial;
|
||||
use crate::types::{Direction, TrialState};
|
||||
|
||||
/// Prune trials that are performing worse than the median of completed trials
|
||||
/// at the same step.
|
||||
///
|
||||
/// This is the most commonly used pruner. It compares the current trial's
|
||||
/// intermediate value at each step with the median of all completed trials'
|
||||
/// values at that same step.
|
||||
///
|
||||
/// Equivalent to `PercentilePruner::new(50.0, direction)`.
|
||||
///
|
||||
/// # Examples
|
||||
///
|
||||
/// ```
|
||||
/// use optimizer::Direction;
|
||||
/// use optimizer::pruner::MedianPruner;
|
||||
///
|
||||
/// // Prune trials worse than median when minimizing, after 5 warmup steps
|
||||
/// let pruner = MedianPruner::new(Direction::Minimize)
|
||||
/// .n_warmup_steps(5)
|
||||
/// .n_min_trials(3);
|
||||
/// ```
|
||||
pub struct MedianPruner {
|
||||
/// The optimization direction.
|
||||
direction: Direction,
|
||||
/// Don't prune in the first N steps (let the trial warm up).
|
||||
n_warmup_steps: u64,
|
||||
/// Require at least N completed trials before pruning.
|
||||
n_min_trials: usize,
|
||||
}
|
||||
|
||||
impl MedianPruner {
|
||||
/// Create a new `MedianPruner` for the given optimization direction.
|
||||
///
|
||||
/// By default, `n_warmup_steps` is 0 and `n_min_trials` is 1.
|
||||
#[must_use]
|
||||
pub fn new(direction: Direction) -> Self {
|
||||
Self {
|
||||
direction,
|
||||
n_warmup_steps: 0,
|
||||
n_min_trials: 1,
|
||||
}
|
||||
}
|
||||
|
||||
/// Set the number of warmup steps. No pruning occurs before this step.
|
||||
#[must_use]
|
||||
pub fn n_warmup_steps(mut self, n: u64) -> Self {
|
||||
self.n_warmup_steps = n;
|
||||
self
|
||||
}
|
||||
|
||||
/// Set the minimum number of completed trials required before pruning.
|
||||
#[must_use]
|
||||
pub fn n_min_trials(mut self, n: usize) -> Self {
|
||||
self.n_min_trials = n;
|
||||
self
|
||||
}
|
||||
}
|
||||
|
||||
impl Pruner for MedianPruner {
|
||||
fn should_prune(
|
||||
&self,
|
||||
_trial_id: u64,
|
||||
step: u64,
|
||||
intermediate_values: &[(u64, f64)],
|
||||
completed_trials: &[CompletedTrial],
|
||||
) -> bool {
|
||||
// 1. Don't prune during warmup
|
||||
if step < self.n_warmup_steps {
|
||||
return false;
|
||||
}
|
||||
|
||||
// Get the current trial's latest value
|
||||
let Some(&(_, current_value)) = intermediate_values.last() else {
|
||||
return false;
|
||||
};
|
||||
|
||||
// 2. Collect values at this step from completed (non-pruned) trials
|
||||
let mut values_at_step: Vec<f64> = completed_trials
|
||||
.iter()
|
||||
.filter(|t| t.state == TrialState::Complete)
|
||||
.filter_map(|t| {
|
||||
t.intermediate_values
|
||||
.iter()
|
||||
.find(|(s, _)| *s == step)
|
||||
.map(|(_, v)| *v)
|
||||
})
|
||||
.collect();
|
||||
|
||||
// 3. Not enough trials
|
||||
if values_at_step.len() < self.n_min_trials {
|
||||
return false;
|
||||
}
|
||||
|
||||
// 4. Compute median (50th percentile)
|
||||
let median = compute_percentile(&mut values_at_step, 50.0);
|
||||
|
||||
// 5. Compare against median based on direction
|
||||
match self.direction {
|
||||
Direction::Minimize => current_value > median,
|
||||
Direction::Maximize => current_value < median,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn compute_median_odd() {
|
||||
assert!((compute_percentile(&mut [3.0, 1.0, 2.0], 50.0) - 2.0).abs() < f64::EPSILON);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn compute_median_even() {
|
||||
assert!((compute_percentile(&mut [4.0, 1.0, 3.0, 2.0], 50.0) - 2.5).abs() < f64::EPSILON);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn compute_median_single() {
|
||||
assert!((compute_percentile(&mut [5.0], 50.0) - 5.0).abs() < f64::EPSILON);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,74 @@
|
||||
//! Pruner trait and implementations for trial pruning.
|
||||
//!
|
||||
//! Pruners decide whether to stop (prune) a trial early based on its
|
||||
//! intermediate values compared to other trials. This is useful for
|
||||
//! discarding unpromising trials before they complete, saving compute.
|
||||
|
||||
mod hyperband;
|
||||
mod median;
|
||||
mod nop;
|
||||
mod patient;
|
||||
pub(crate) mod percentile;
|
||||
mod successive_halving;
|
||||
mod threshold;
|
||||
mod wilcoxon;
|
||||
|
||||
pub use hyperband::HyperbandPruner;
|
||||
pub use median::MedianPruner;
|
||||
pub use nop::NopPruner;
|
||||
pub use patient::PatientPruner;
|
||||
pub use percentile::PercentilePruner;
|
||||
pub use successive_halving::SuccessiveHalvingPruner;
|
||||
pub use threshold::ThresholdPruner;
|
||||
pub use wilcoxon::WilcoxonPruner;
|
||||
|
||||
use crate::sampler::CompletedTrial;
|
||||
|
||||
/// Trait for pluggable trial pruning strategies.
|
||||
///
|
||||
/// Pruners are consulted after each intermediate value is reported to
|
||||
/// decide whether the trial should be stopped early. The trait requires
|
||||
/// `Send + Sync` to support concurrent and async optimization.
|
||||
///
|
||||
/// # Implementing a custom pruner
|
||||
///
|
||||
/// ```
|
||||
/// use optimizer::pruner::Pruner;
|
||||
/// use optimizer::sampler::CompletedTrial;
|
||||
///
|
||||
/// struct MyPruner {
|
||||
/// threshold: f64,
|
||||
/// }
|
||||
///
|
||||
/// impl Pruner for MyPruner {
|
||||
/// fn should_prune(
|
||||
/// &self,
|
||||
/// _trial_id: u64,
|
||||
/// _step: u64,
|
||||
/// intermediate_values: &[(u64, f64)],
|
||||
/// _completed_trials: &[CompletedTrial],
|
||||
/// ) -> bool {
|
||||
/// // Prune if the latest value exceeds the threshold
|
||||
/// intermediate_values
|
||||
/// .last()
|
||||
/// .is_some_and(|&(_, v)| v > self.threshold)
|
||||
/// }
|
||||
/// }
|
||||
/// ```
|
||||
pub trait Pruner: Send + Sync {
|
||||
/// Decide whether to prune a trial at the given step.
|
||||
///
|
||||
/// # Arguments
|
||||
///
|
||||
/// * `trial_id` - The current trial's ID.
|
||||
/// * `step` - The step at which the intermediate value was reported.
|
||||
/// * `intermediate_values` - All `(step, value)` pairs reported so far for this trial.
|
||||
/// * `completed_trials` - History of all completed trials (for comparison).
|
||||
fn should_prune(
|
||||
&self,
|
||||
trial_id: u64,
|
||||
step: u64,
|
||||
intermediate_values: &[(u64, f64)],
|
||||
completed_trials: &[CompletedTrial],
|
||||
) -> bool;
|
||||
}
|
||||
@@ -0,0 +1,17 @@
|
||||
use super::Pruner;
|
||||
use crate::sampler::CompletedTrial;
|
||||
|
||||
/// A pruner that never prunes. This is the default when no pruner is configured.
|
||||
pub struct NopPruner;
|
||||
|
||||
impl Pruner for NopPruner {
|
||||
fn should_prune(
|
||||
&self,
|
||||
_trial_id: u64,
|
||||
_step: u64,
|
||||
_intermediate_values: &[(u64, f64)],
|
||||
_completed_trials: &[CompletedTrial],
|
||||
) -> bool {
|
||||
false
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,160 @@
|
||||
use std::collections::HashMap;
|
||||
use std::sync::Mutex;
|
||||
|
||||
use super::Pruner;
|
||||
use crate::sampler::CompletedTrial;
|
||||
|
||||
/// Wraps another pruner and adds a patience window.
|
||||
///
|
||||
/// The inner pruner must recommend pruning for `patience` consecutive
|
||||
/// steps before this pruner actually prunes the trial. This is useful
|
||||
/// to prevent premature pruning when intermediate values are noisy.
|
||||
///
|
||||
/// # Examples
|
||||
///
|
||||
/// ```
|
||||
/// use optimizer::pruner::{PatientPruner, ThresholdPruner};
|
||||
///
|
||||
/// // Only prune after the threshold pruner recommends pruning 3 times in a row
|
||||
/// let inner = ThresholdPruner::new().upper(100.0);
|
||||
/// let pruner = PatientPruner::new(inner, 3);
|
||||
/// ```
|
||||
pub struct PatientPruner {
|
||||
inner: Box<dyn Pruner>,
|
||||
patience: u64,
|
||||
/// Track consecutive prune recommendations per trial.
|
||||
consecutive_counts: Mutex<HashMap<u64, u64>>,
|
||||
}
|
||||
|
||||
impl PatientPruner {
|
||||
/// Create a new `PatientPruner` wrapping the given inner pruner.
|
||||
///
|
||||
/// The inner pruner must recommend pruning for `patience` consecutive
|
||||
/// calls before this pruner returns `true`.
|
||||
pub fn new(inner: impl Pruner + 'static, patience: u64) -> Self {
|
||||
Self {
|
||||
inner: Box::new(inner),
|
||||
patience,
|
||||
consecutive_counts: Mutex::new(HashMap::new()),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
impl Pruner for PatientPruner {
|
||||
fn should_prune(
|
||||
&self,
|
||||
trial_id: u64,
|
||||
step: u64,
|
||||
intermediate_values: &[(u64, f64)],
|
||||
completed_trials: &[CompletedTrial],
|
||||
) -> bool {
|
||||
let inner_says_prune =
|
||||
self.inner
|
||||
.should_prune(trial_id, step, intermediate_values, completed_trials);
|
||||
let mut counts = self.consecutive_counts.lock().expect("lock poisoned");
|
||||
let count = counts.entry(trial_id).or_insert(0);
|
||||
if inner_says_prune {
|
||||
*count += 1;
|
||||
*count >= self.patience
|
||||
} else {
|
||||
*count = 0;
|
||||
false
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use crate::pruner::ThresholdPruner;
|
||||
|
||||
/// A test pruner that always returns the given value.
|
||||
struct ConstPruner(bool);
|
||||
|
||||
impl Pruner for ConstPruner {
|
||||
fn should_prune(
|
||||
&self,
|
||||
_trial_id: u64,
|
||||
_step: u64,
|
||||
_intermediate_values: &[(u64, f64)],
|
||||
_completed_trials: &[CompletedTrial],
|
||||
) -> bool {
|
||||
self.0
|
||||
}
|
||||
}
|
||||
|
||||
/// A pruner that returns values from a sequence.
|
||||
struct SequencePruner(Mutex<Vec<bool>>);
|
||||
|
||||
impl Pruner for SequencePruner {
|
||||
fn should_prune(
|
||||
&self,
|
||||
_trial_id: u64,
|
||||
_step: u64,
|
||||
_intermediate_values: &[(u64, f64)],
|
||||
_completed_trials: &[CompletedTrial],
|
||||
) -> bool {
|
||||
self.0.lock().expect("lock poisoned").remove(0)
|
||||
}
|
||||
}
|
||||
|
||||
fn call(pruner: &PatientPruner, trial_id: u64, step: u64) -> bool {
|
||||
pruner.should_prune(trial_id, step, &[(step, 0.0)], &[])
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn patience_1_behaves_like_inner() {
|
||||
let pruner = PatientPruner::new(ConstPruner(true), 1);
|
||||
assert!(call(&pruner, 0, 0));
|
||||
assert!(call(&pruner, 0, 1));
|
||||
|
||||
let pruner = PatientPruner::new(ConstPruner(false), 1);
|
||||
assert!(!call(&pruner, 0, 0));
|
||||
assert!(!call(&pruner, 0, 1));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn patience_3_requires_consecutive_recommendations() {
|
||||
let pruner = PatientPruner::new(ConstPruner(true), 3);
|
||||
assert!(!call(&pruner, 0, 0)); // count=1
|
||||
assert!(!call(&pruner, 0, 1)); // count=2
|
||||
assert!(call(&pruner, 0, 2)); // count=3 → prune
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn counter_resets_on_no_prune() {
|
||||
// Sequence: prune, prune, no-prune, prune, prune, prune
|
||||
let seq = vec![true, true, false, true, true, true];
|
||||
let pruner = PatientPruner::new(SequencePruner(Mutex::new(seq)), 3);
|
||||
|
||||
assert!(!call(&pruner, 0, 0)); // count=1
|
||||
assert!(!call(&pruner, 0, 1)); // count=2
|
||||
assert!(!call(&pruner, 0, 2)); // reset → count=0
|
||||
assert!(!call(&pruner, 0, 3)); // count=1
|
||||
assert!(!call(&pruner, 0, 4)); // count=2
|
||||
assert!(call(&pruner, 0, 5)); // count=3 → prune
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn independent_per_trial() {
|
||||
let pruner = PatientPruner::new(ConstPruner(true), 2);
|
||||
assert!(!call(&pruner, 0, 0)); // trial 0: count=1
|
||||
assert!(!call(&pruner, 1, 0)); // trial 1: count=1
|
||||
assert!(call(&pruner, 0, 1)); // trial 0: count=2 → prune
|
||||
assert!(!call(&pruner, 2, 0)); // trial 2: count=1
|
||||
assert!(call(&pruner, 1, 1)); // trial 1: count=2 → prune
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn works_with_threshold_pruner() {
|
||||
let inner = ThresholdPruner::new().upper(10.0);
|
||||
let pruner = PatientPruner::new(inner, 2);
|
||||
|
||||
// Value below threshold → inner says no
|
||||
assert!(!pruner.should_prune(0, 0, &[(0, 5.0)], &[]));
|
||||
// Value above threshold → inner says yes, count=1
|
||||
assert!(!pruner.should_prune(0, 1, &[(0, 5.0), (1, 15.0)], &[]));
|
||||
// Value above threshold again → count=2 → prune
|
||||
assert!(pruner.should_prune(0, 2, &[(0, 5.0), (1, 15.0), (2, 20.0)], &[]));
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,294 @@
|
||||
use super::Pruner;
|
||||
use crate::sampler::CompletedTrial;
|
||||
use crate::types::{Direction, TrialState};
|
||||
|
||||
/// Prune trials that are not in the top `percentile`% of completed trials
|
||||
/// at the same training step.
|
||||
///
|
||||
/// `PercentilePruner::new(50.0, direction)` is equivalent to `MedianPruner`.
|
||||
/// `PercentilePruner::new(25.0, direction)` keeps only the top 25% of trials.
|
||||
///
|
||||
/// # Examples
|
||||
///
|
||||
/// ```
|
||||
/// use optimizer::Direction;
|
||||
/// use optimizer::pruner::PercentilePruner;
|
||||
///
|
||||
/// // Keep only the top 25% of trials (aggressive pruning)
|
||||
/// let pruner = PercentilePruner::new(25.0, Direction::Minimize)
|
||||
/// .n_warmup_steps(5)
|
||||
/// .n_min_trials(3);
|
||||
/// ```
|
||||
pub struct PercentilePruner {
|
||||
/// Keep trials in the top `percentile`%. Range: (0.0, 100.0).
|
||||
percentile: f64,
|
||||
/// Don't prune in the first N steps (let the trial warm up).
|
||||
n_warmup_steps: u64,
|
||||
/// Require at least N completed trials before pruning.
|
||||
n_min_trials: usize,
|
||||
/// The optimization direction.
|
||||
direction: Direction,
|
||||
}
|
||||
|
||||
impl PercentilePruner {
|
||||
/// Create a new `PercentilePruner` for the given percentile and direction.
|
||||
///
|
||||
/// The `percentile` value must be in `(0.0, 100.0)`.
|
||||
/// A percentile of 50.0 is equivalent to median pruning.
|
||||
///
|
||||
/// # Panics
|
||||
///
|
||||
/// Panics if `percentile` is not in `(0.0, 100.0)`.
|
||||
#[must_use]
|
||||
pub fn new(percentile: f64, direction: Direction) -> Self {
|
||||
assert!(
|
||||
percentile > 0.0 && percentile < 100.0,
|
||||
"percentile must be in (0.0, 100.0), got {percentile}"
|
||||
);
|
||||
Self {
|
||||
percentile,
|
||||
n_warmup_steps: 0,
|
||||
n_min_trials: 1,
|
||||
direction,
|
||||
}
|
||||
}
|
||||
|
||||
/// Set the number of warmup steps. No pruning occurs before this step.
|
||||
#[must_use]
|
||||
pub fn n_warmup_steps(mut self, n: u64) -> Self {
|
||||
self.n_warmup_steps = n;
|
||||
self
|
||||
}
|
||||
|
||||
/// Set the minimum number of completed trials required before pruning.
|
||||
#[must_use]
|
||||
pub fn n_min_trials(mut self, n: usize) -> Self {
|
||||
self.n_min_trials = n;
|
||||
self
|
||||
}
|
||||
}
|
||||
|
||||
impl Pruner for PercentilePruner {
|
||||
fn should_prune(
|
||||
&self,
|
||||
_trial_id: u64,
|
||||
step: u64,
|
||||
intermediate_values: &[(u64, f64)],
|
||||
completed_trials: &[CompletedTrial],
|
||||
) -> bool {
|
||||
// 1. Don't prune during warmup
|
||||
if step < self.n_warmup_steps {
|
||||
return false;
|
||||
}
|
||||
|
||||
// Get the current trial's latest value
|
||||
let Some(&(_, current_value)) = intermediate_values.last() else {
|
||||
return false;
|
||||
};
|
||||
|
||||
// 2. Collect values at this step from completed (non-pruned) trials
|
||||
let mut values_at_step: Vec<f64> = completed_trials
|
||||
.iter()
|
||||
.filter(|t| t.state == TrialState::Complete)
|
||||
.filter_map(|t| {
|
||||
t.intermediate_values
|
||||
.iter()
|
||||
.find(|(s, _)| *s == step)
|
||||
.map(|(_, v)| *v)
|
||||
})
|
||||
.collect();
|
||||
|
||||
// 3. Not enough trials
|
||||
if values_at_step.len() < self.n_min_trials {
|
||||
return false;
|
||||
}
|
||||
|
||||
// 4. Compute percentile threshold
|
||||
let threshold = compute_percentile(&mut values_at_step, self.percentile);
|
||||
|
||||
// 5. Compare against threshold based on direction
|
||||
match self.direction {
|
||||
Direction::Minimize => current_value > threshold,
|
||||
Direction::Maximize => current_value < threshold,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Compute the given percentile of a non-empty slice. Sorts the slice in place.
|
||||
///
|
||||
/// Uses linear interpolation between the two nearest ranks.
|
||||
#[allow(
|
||||
clippy::cast_precision_loss,
|
||||
clippy::cast_possible_truncation,
|
||||
clippy::cast_sign_loss
|
||||
)]
|
||||
pub(crate) fn compute_percentile(values: &mut [f64], percentile: f64) -> f64 {
|
||||
values.sort_unstable_by(|a, b| a.partial_cmp(b).unwrap_or(core::cmp::Ordering::Equal));
|
||||
let len = values.len();
|
||||
if len == 1 {
|
||||
return values[0];
|
||||
}
|
||||
// Rank in [0, len-1] range
|
||||
let rank = percentile / 100.0 * (len - 1) as f64;
|
||||
let lower = rank.floor() as usize;
|
||||
let upper = rank.ceil() as usize;
|
||||
if lower == upper {
|
||||
values[lower]
|
||||
} else {
|
||||
let frac = rank - lower as f64;
|
||||
values[lower] * (1.0 - frac) + values[upper] * frac
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn compute_percentile_median_odd() {
|
||||
// Percentile 50 on odd-length slice = median
|
||||
let val = compute_percentile(&mut [3.0, 1.0, 2.0], 50.0);
|
||||
assert!((val - 2.0).abs() < f64::EPSILON);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn compute_percentile_median_even() {
|
||||
// Percentile 50 on even-length slice = median (interpolated)
|
||||
let val = compute_percentile(&mut [4.0, 1.0, 3.0, 2.0], 50.0);
|
||||
assert!((val - 2.5).abs() < f64::EPSILON);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn compute_percentile_25() {
|
||||
// [1.0, 2.0, 3.0, 4.0], rank = 0.25 * 3 = 0.75
|
||||
// interpolate: 1.0 * 0.25 + 2.0 * 0.75 = 1.75
|
||||
let val = compute_percentile(&mut [4.0, 1.0, 3.0, 2.0], 25.0);
|
||||
assert!((val - 1.75).abs() < f64::EPSILON);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn compute_percentile_75() {
|
||||
// [1.0, 2.0, 3.0, 4.0], rank = 0.75 * 3 = 2.25
|
||||
// interpolate: 3.0 * 0.75 + 4.0 * 0.25 = 3.25
|
||||
let val = compute_percentile(&mut [4.0, 1.0, 3.0, 2.0], 75.0);
|
||||
assert!((val - 3.25).abs() < f64::EPSILON);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn compute_percentile_single() {
|
||||
let val = compute_percentile(&mut [5.0], 50.0);
|
||||
assert!((val - 5.0).abs() < f64::EPSILON);
|
||||
}
|
||||
|
||||
#[test]
|
||||
#[should_panic(expected = "percentile must be in (0.0, 100.0)")]
|
||||
fn new_rejects_zero() {
|
||||
let _ = PercentilePruner::new(0.0, Direction::Minimize);
|
||||
}
|
||||
|
||||
#[test]
|
||||
#[should_panic(expected = "percentile must be in (0.0, 100.0)")]
|
||||
fn new_rejects_hundred() {
|
||||
let _ = PercentilePruner::new(100.0, Direction::Minimize);
|
||||
}
|
||||
|
||||
fn make_completed_trial(id: u64, values: &[(u64, f64)]) -> CompletedTrial {
|
||||
use std::collections::HashMap;
|
||||
|
||||
use crate::parameter::ParamId;
|
||||
|
||||
CompletedTrial::with_intermediate_values(
|
||||
id,
|
||||
HashMap::<ParamId, crate::ParamValue>::new(),
|
||||
HashMap::new(),
|
||||
HashMap::new(),
|
||||
0.0,
|
||||
values.to_vec(),
|
||||
HashMap::new(),
|
||||
)
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn percentile_50_matches_median_behavior() {
|
||||
let pruner = PercentilePruner::new(50.0, Direction::Minimize);
|
||||
let completed = vec![
|
||||
make_completed_trial(0, &[(0, 1.0), (1, 2.0)]),
|
||||
make_completed_trial(1, &[(0, 3.0), (1, 4.0)]),
|
||||
make_completed_trial(2, &[(0, 5.0), (1, 6.0)]),
|
||||
];
|
||||
// Median at step 1 is 4.0
|
||||
// Value 5.0 > 4.0 → prune
|
||||
assert!(pruner.should_prune(3, 1, &[(0, 3.0), (1, 5.0)], &completed));
|
||||
// Value 3.0 < 4.0 → keep
|
||||
assert!(!pruner.should_prune(3, 1, &[(0, 3.0), (1, 3.0)], &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn percentile_25_is_more_aggressive() {
|
||||
let pruner_25 = PercentilePruner::new(25.0, Direction::Minimize);
|
||||
let pruner_75 = PercentilePruner::new(75.0, Direction::Minimize);
|
||||
let completed = vec![
|
||||
make_completed_trial(0, &[(0, 1.0)]),
|
||||
make_completed_trial(1, &[(0, 2.0)]),
|
||||
make_completed_trial(2, &[(0, 3.0)]),
|
||||
make_completed_trial(3, &[(0, 4.0)]),
|
||||
];
|
||||
// 25th percentile at step 0: 1.75
|
||||
// 75th percentile at step 0: 3.25
|
||||
// Value 2.5: above 25th (prune), below 75th (keep)
|
||||
assert!(pruner_25.should_prune(4, 0, &[(0, 2.5)], &completed));
|
||||
assert!(!pruner_75.should_prune(4, 0, &[(0, 2.5)], &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn warmup_prevents_pruning() {
|
||||
let pruner = PercentilePruner::new(50.0, Direction::Minimize).n_warmup_steps(5);
|
||||
let completed = vec![make_completed_trial(0, &[(0, 1.0)])];
|
||||
// Step 3 < warmup 5 → no prune even with bad value
|
||||
assert!(!pruner.should_prune(1, 3, &[(3, 100.0)], &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn n_min_trials_prevents_pruning() {
|
||||
let pruner = PercentilePruner::new(50.0, Direction::Minimize).n_min_trials(5);
|
||||
let completed = vec![
|
||||
make_completed_trial(0, &[(0, 1.0)]),
|
||||
make_completed_trial(1, &[(0, 2.0)]),
|
||||
];
|
||||
// Only 2 trials, need 5 → no prune
|
||||
assert!(!pruner.should_prune(2, 0, &[(0, 100.0)], &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn maximize_direction() {
|
||||
let pruner = PercentilePruner::new(50.0, Direction::Maximize);
|
||||
let completed = vec![
|
||||
make_completed_trial(0, &[(0, 1.0)]),
|
||||
make_completed_trial(1, &[(0, 3.0)]),
|
||||
make_completed_trial(2, &[(0, 5.0)]),
|
||||
];
|
||||
// Median at step 0 is 3.0
|
||||
// Value 2.0 < 3.0 → prune (maximize wants higher)
|
||||
assert!(pruner.should_prune(3, 0, &[(0, 2.0)], &completed));
|
||||
// Value 4.0 > 3.0 → keep
|
||||
assert!(!pruner.should_prune(3, 0, &[(0, 4.0)], &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn near_boundary_percentiles() {
|
||||
let pruner_low = PercentilePruner::new(1.0, Direction::Minimize);
|
||||
let pruner_high = PercentilePruner::new(99.0, Direction::Minimize);
|
||||
let completed = vec![
|
||||
make_completed_trial(0, &[(0, 1.0)]),
|
||||
make_completed_trial(1, &[(0, 2.0)]),
|
||||
make_completed_trial(2, &[(0, 3.0)]),
|
||||
make_completed_trial(3, &[(0, 100.0)]),
|
||||
];
|
||||
// Percentile 1 is very aggressive (threshold near 1.0)
|
||||
// Value 1.5 should be pruned
|
||||
assert!(pruner_low.should_prune(4, 0, &[(0, 1.5)], &completed));
|
||||
// Percentile 99 is very lenient (threshold near 100.0)
|
||||
// Value 50.0 should not be pruned
|
||||
assert!(!pruner_high.should_prune(4, 0, &[(0, 50.0)], &completed));
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,466 @@
|
||||
use super::Pruner;
|
||||
use crate::sampler::CompletedTrial;
|
||||
use crate::types::{Direction, TrialState};
|
||||
|
||||
/// Successive Halving pruner based on the SHA algorithm.
|
||||
///
|
||||
/// Trials are evaluated at exponentially-spaced "rungs". At each rung,
|
||||
/// only the top 1/eta fraction of trials survive to the next rung.
|
||||
///
|
||||
/// For example, with `min_resource=1`, `max_resource=81`, `reduction_factor=3`:
|
||||
/// - Rung 0: evaluate at step 1, keep top 1/3
|
||||
/// - Rung 1: evaluate at step 3, keep top 1/3
|
||||
/// - Rung 2: evaluate at step 9, keep top 1/3
|
||||
/// - Rung 3: evaluate at step 27, keep top 1/3
|
||||
/// - Rung 4: evaluate at step 81 (full budget)
|
||||
///
|
||||
/// # Examples
|
||||
///
|
||||
/// ```
|
||||
/// use optimizer::Direction;
|
||||
/// use optimizer::pruner::SuccessiveHalvingPruner;
|
||||
///
|
||||
/// let pruner = SuccessiveHalvingPruner::new()
|
||||
/// .min_resource(1)
|
||||
/// .max_resource(81)
|
||||
/// .reduction_factor(3)
|
||||
/// .direction(Direction::Minimize);
|
||||
/// ```
|
||||
pub struct SuccessiveHalvingPruner {
|
||||
min_resource: u64,
|
||||
max_resource: u64,
|
||||
reduction_factor: u64,
|
||||
min_early_stopping_rate: u64,
|
||||
direction: Direction,
|
||||
}
|
||||
|
||||
impl SuccessiveHalvingPruner {
|
||||
/// Create a new `SuccessiveHalvingPruner` with default parameters.
|
||||
///
|
||||
/// Defaults: `min_resource=1`, `max_resource=81`, `reduction_factor=3`,
|
||||
/// `min_early_stopping_rate=0`, `direction=Minimize`.
|
||||
#[must_use]
|
||||
pub fn new() -> Self {
|
||||
Self {
|
||||
min_resource: 1,
|
||||
max_resource: 81,
|
||||
reduction_factor: 3,
|
||||
min_early_stopping_rate: 0,
|
||||
direction: Direction::Minimize,
|
||||
}
|
||||
}
|
||||
|
||||
/// Set the minimum resource (budget) per trial.
|
||||
///
|
||||
/// # Panics
|
||||
///
|
||||
/// Panics if `r` is 0.
|
||||
#[must_use]
|
||||
pub fn min_resource(mut self, r: u64) -> Self {
|
||||
assert!(r > 0, "min_resource must be > 0, got {r}");
|
||||
self.min_resource = r;
|
||||
self
|
||||
}
|
||||
|
||||
/// Set the maximum resource (budget) per trial.
|
||||
///
|
||||
/// # Panics
|
||||
///
|
||||
/// Panics if `r` is 0.
|
||||
#[must_use]
|
||||
pub fn max_resource(mut self, r: u64) -> Self {
|
||||
assert!(r > 0, "max_resource must be > 0, got {r}");
|
||||
self.max_resource = r;
|
||||
self
|
||||
}
|
||||
|
||||
/// Set the reduction factor (eta). At each rung, the top 1/eta trials survive.
|
||||
///
|
||||
/// # Panics
|
||||
///
|
||||
/// Panics if `eta` is less than 2.
|
||||
#[must_use]
|
||||
pub fn reduction_factor(mut self, eta: u64) -> Self {
|
||||
assert!(eta >= 2, "reduction_factor must be >= 2, got {eta}");
|
||||
self.reduction_factor = eta;
|
||||
self
|
||||
}
|
||||
|
||||
/// Set the minimum early stopping rate. Skips the first N rungs.
|
||||
#[must_use]
|
||||
pub fn min_early_stopping_rate(mut self, n: u64) -> Self {
|
||||
self.min_early_stopping_rate = n;
|
||||
self
|
||||
}
|
||||
|
||||
/// Set the optimization direction.
|
||||
#[must_use]
|
||||
pub fn direction(mut self, d: Direction) -> Self {
|
||||
self.direction = d;
|
||||
self
|
||||
}
|
||||
|
||||
/// Compute the rung steps: `[min_resource * eta^(s), ...]` up to `max_resource`,
|
||||
/// skipping the first `min_early_stopping_rate` rungs.
|
||||
fn rung_steps(&self) -> Vec<u64> {
|
||||
let eta = self.reduction_factor;
|
||||
let mut steps = Vec::new();
|
||||
let mut rung: u32 = 0;
|
||||
while let Some(power) = eta.checked_pow(rung) {
|
||||
let step = self.min_resource.saturating_mul(power);
|
||||
if step > self.max_resource {
|
||||
break;
|
||||
}
|
||||
if u64::from(rung) >= self.min_early_stopping_rate {
|
||||
steps.push(step);
|
||||
}
|
||||
rung += 1;
|
||||
}
|
||||
steps
|
||||
}
|
||||
}
|
||||
|
||||
impl Default for SuccessiveHalvingPruner {
|
||||
fn default() -> Self {
|
||||
Self::new()
|
||||
}
|
||||
}
|
||||
|
||||
#[allow(clippy::cast_precision_loss)]
|
||||
impl Pruner for SuccessiveHalvingPruner {
|
||||
fn should_prune(
|
||||
&self,
|
||||
_trial_id: u64,
|
||||
step: u64,
|
||||
intermediate_values: &[(u64, f64)],
|
||||
completed_trials: &[CompletedTrial],
|
||||
) -> bool {
|
||||
let rungs = self.rung_steps();
|
||||
|
||||
// Find the highest rung step <= current step
|
||||
let Some(&rung_step) = rungs.iter().rev().find(|&&r| r <= step) else {
|
||||
// No rung matches (before the first rung) → don't prune
|
||||
return false;
|
||||
};
|
||||
|
||||
// If this is the last rung (full budget), don't prune
|
||||
if rung_step >= self.max_resource {
|
||||
return false;
|
||||
}
|
||||
|
||||
// Get the current trial's value at this rung step
|
||||
let Some(&(_, current_value)) = intermediate_values.iter().find(|(s, _)| *s == rung_step)
|
||||
else {
|
||||
// Trial hasn't reported a value at this exact rung step.
|
||||
// Use the latest intermediate value at or before the rung step instead.
|
||||
let Some(&(_, current_value)) = intermediate_values
|
||||
.iter()
|
||||
.rev()
|
||||
.find(|(s, _)| *s <= rung_step)
|
||||
else {
|
||||
return false;
|
||||
};
|
||||
return self.is_pruned_at_rung(current_value, rung_step, completed_trials);
|
||||
};
|
||||
|
||||
self.is_pruned_at_rung(current_value, rung_step, completed_trials)
|
||||
}
|
||||
}
|
||||
|
||||
impl SuccessiveHalvingPruner {
|
||||
/// Determine whether a trial with `current_value` should be pruned at the given rung.
|
||||
#[allow(
|
||||
clippy::cast_precision_loss,
|
||||
clippy::cast_possible_truncation,
|
||||
clippy::cast_sign_loss
|
||||
)]
|
||||
fn is_pruned_at_rung(
|
||||
&self,
|
||||
current_value: f64,
|
||||
rung_step: u64,
|
||||
completed_trials: &[CompletedTrial],
|
||||
) -> bool {
|
||||
let eta = self.reduction_factor as usize;
|
||||
|
||||
// Collect values at this rung step from all trials that reached it
|
||||
let mut values_at_rung: Vec<f64> = completed_trials
|
||||
.iter()
|
||||
.filter(|t| t.state == TrialState::Complete || t.state == TrialState::Pruned)
|
||||
.filter_map(|t| {
|
||||
t.intermediate_values
|
||||
.iter()
|
||||
.find(|(s, _)| *s == rung_step)
|
||||
.map(|(_, v)| *v)
|
||||
})
|
||||
.collect();
|
||||
|
||||
// Need at least eta trials to make a meaningful comparison
|
||||
// (with fewer trials, we can't determine the top 1/eta fraction)
|
||||
if values_at_rung.len() < eta {
|
||||
return false;
|
||||
}
|
||||
|
||||
// Include the current trial's value for ranking
|
||||
values_at_rung.push(current_value);
|
||||
|
||||
// Sort based on direction: best values first
|
||||
values_at_rung
|
||||
.sort_unstable_by(|a, b| a.partial_cmp(b).unwrap_or(core::cmp::Ordering::Equal));
|
||||
if self.direction == Direction::Maximize {
|
||||
values_at_rung.reverse();
|
||||
}
|
||||
|
||||
// Keep top 1/eta fraction
|
||||
let n_keep = (values_at_rung.len() as f64 / eta as f64).ceil() as usize;
|
||||
let threshold_idx = n_keep.max(1) - 1;
|
||||
let threshold = values_at_rung[threshold_idx];
|
||||
|
||||
// Prune if current value is worse than the threshold
|
||||
match self.direction {
|
||||
Direction::Minimize => current_value > threshold,
|
||||
Direction::Maximize => current_value < threshold,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
#[allow(clippy::cast_precision_loss)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
fn make_trial(id: u64, values: &[(u64, f64)]) -> CompletedTrial {
|
||||
use std::collections::HashMap;
|
||||
|
||||
use crate::parameter::ParamId;
|
||||
|
||||
CompletedTrial::with_intermediate_values(
|
||||
id,
|
||||
HashMap::<ParamId, crate::ParamValue>::new(),
|
||||
HashMap::new(),
|
||||
HashMap::new(),
|
||||
0.0,
|
||||
values.to_vec(),
|
||||
HashMap::new(),
|
||||
)
|
||||
}
|
||||
|
||||
fn make_pruned_trial(id: u64, values: &[(u64, f64)]) -> CompletedTrial {
|
||||
let mut t = make_trial(id, values);
|
||||
t.state = TrialState::Pruned;
|
||||
t
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rung_steps_default() {
|
||||
let pruner = SuccessiveHalvingPruner::new();
|
||||
let rungs = pruner.rung_steps();
|
||||
// min=1, max=81, eta=3 → 1, 3, 9, 27, 81
|
||||
assert_eq!(rungs, vec![1, 3, 9, 27, 81]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rung_steps_custom() {
|
||||
let pruner = SuccessiveHalvingPruner::new()
|
||||
.min_resource(2)
|
||||
.max_resource(32)
|
||||
.reduction_factor(2);
|
||||
let rungs = pruner.rung_steps();
|
||||
// 2, 4, 8, 16, 32
|
||||
assert_eq!(rungs, vec![2, 4, 8, 16, 32]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rung_steps_with_early_stopping_rate() {
|
||||
let pruner = SuccessiveHalvingPruner::new().min_early_stopping_rate(2);
|
||||
let rungs = pruner.rung_steps();
|
||||
// Skip rung 0 (step=1) and rung 1 (step=3), keep rung 2+ (9, 27, 81)
|
||||
assert_eq!(rungs, vec![9, 27, 81]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn no_prune_before_first_rung() {
|
||||
let pruner = SuccessiveHalvingPruner::new()
|
||||
.min_resource(10)
|
||||
.max_resource(100)
|
||||
.reduction_factor(3);
|
||||
let completed = vec![
|
||||
make_trial(0, &[(5, 1.0)]),
|
||||
make_trial(1, &[(5, 2.0)]),
|
||||
make_trial(2, &[(5, 3.0)]),
|
||||
];
|
||||
// Step 5 is before the first rung (10)
|
||||
assert!(!pruner.should_prune(3, 5, &[(5, 100.0)], &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn no_prune_with_single_trial() {
|
||||
let pruner = SuccessiveHalvingPruner::new();
|
||||
let completed = vec![make_trial(0, &[(1, 5.0)]), make_trial(1, &[(1, 3.0)])];
|
||||
// Only 2 completed trials at rung + 1 current = 3 total, threshold = ceil(3/3) = 1
|
||||
// With eta=3, we need at least 3 completed trials
|
||||
assert!(!pruner.should_prune(2, 1, &[(1, 10.0)], &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn prune_worst_trials_at_rung() {
|
||||
let pruner = SuccessiveHalvingPruner::new().direction(Direction::Minimize);
|
||||
|
||||
// 9 completed trials at rung step=1, with values 1..=9
|
||||
let completed: Vec<_> = (0..9)
|
||||
.map(|i| make_trial(i, &[(1, (i + 1) as f64)]))
|
||||
.collect();
|
||||
|
||||
// With eta=3, keep top 1/3. 10 total values → ceil(10/3) = 4 kept
|
||||
// Best 4 values: 1, 2, 3, 4. Threshold = 4.0
|
||||
// Value 3.0 → keep (in top 1/3)
|
||||
assert!(!pruner.should_prune(9, 1, &[(1, 3.0)], &completed));
|
||||
// Value 5.0 → prune (not in top 1/3)
|
||||
assert!(pruner.should_prune(9, 1, &[(1, 5.0)], &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn top_fraction_survives() {
|
||||
let pruner = SuccessiveHalvingPruner::new().direction(Direction::Minimize);
|
||||
|
||||
// 6 completed trials at step=1
|
||||
let completed: Vec<_> = (0..6)
|
||||
.map(|i| make_trial(i, &[(1, (i + 1) as f64)]))
|
||||
.collect();
|
||||
|
||||
// 7 total (6 + current). ceil(7/3) = 3 keep. Threshold = 3.0
|
||||
// Value 2.0 → keep
|
||||
assert!(!pruner.should_prune(6, 1, &[(1, 2.0)], &completed));
|
||||
// Value 3.0 → keep (at threshold)
|
||||
assert!(!pruner.should_prune(6, 1, &[(1, 3.0)], &completed));
|
||||
// Value 4.0 → prune
|
||||
assert!(pruner.should_prune(6, 1, &[(1, 4.0)], &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn maximize_direction() {
|
||||
let pruner = SuccessiveHalvingPruner::new().direction(Direction::Maximize);
|
||||
|
||||
let completed: Vec<_> = (0..6)
|
||||
.map(|i| make_trial(i, &[(1, (i + 1) as f64)]))
|
||||
.collect();
|
||||
|
||||
// 7 total. For maximize, best = highest. ceil(7/3)=3. Top 3: 6,5,4. Threshold=4.0
|
||||
// Value 5.0 → keep
|
||||
assert!(!pruner.should_prune(6, 1, &[(1, 5.0)], &completed));
|
||||
// Value 4.0 → keep (at threshold)
|
||||
assert!(!pruner.should_prune(6, 1, &[(1, 4.0)], &completed));
|
||||
// Value 3.0 → prune
|
||||
assert!(pruner.should_prune(6, 1, &[(1, 3.0)], &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn reduction_factor_2() {
|
||||
let pruner = SuccessiveHalvingPruner::new()
|
||||
.reduction_factor(2)
|
||||
.min_resource(1)
|
||||
.max_resource(16)
|
||||
.direction(Direction::Minimize);
|
||||
|
||||
// Rungs: 1, 2, 4, 8, 16
|
||||
assert_eq!(pruner.rung_steps(), vec![1, 2, 4, 8, 16]);
|
||||
|
||||
// 4 completed trials at rung step=1
|
||||
let completed: Vec<_> = (0..4)
|
||||
.map(|i| make_trial(i, &[(1, (i + 1) as f64)]))
|
||||
.collect();
|
||||
|
||||
// With eta=2, 5 total. ceil(5/2) = 3 keep. Threshold = 3.0
|
||||
// Value 3.0 → keep
|
||||
assert!(!pruner.should_prune(4, 1, &[(1, 3.0)], &completed));
|
||||
// Value 4.0 → prune
|
||||
assert!(pruner.should_prune(4, 1, &[(1, 4.0)], &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn reduction_factor_4() {
|
||||
let pruner = SuccessiveHalvingPruner::new()
|
||||
.reduction_factor(4)
|
||||
.min_resource(1)
|
||||
.max_resource(64)
|
||||
.direction(Direction::Minimize);
|
||||
|
||||
// Rungs: 1, 4, 16, 64
|
||||
assert_eq!(pruner.rung_steps(), vec![1, 4, 16, 64]);
|
||||
|
||||
// 12 completed trials at rung step=1
|
||||
let completed: Vec<_> = (0..12)
|
||||
.map(|i| make_trial(i, &[(1, (i + 1) as f64)]))
|
||||
.collect();
|
||||
|
||||
// With eta=4, 13 total. ceil(13/4) = 4 keep. Threshold = 4.0
|
||||
// Value 4.0 → keep
|
||||
assert!(!pruner.should_prune(12, 1, &[(1, 4.0)], &completed));
|
||||
// Value 5.0 → prune
|
||||
assert!(pruner.should_prune(12, 1, &[(1, 5.0)], &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn non_contiguous_steps() {
|
||||
let pruner = SuccessiveHalvingPruner::new().direction(Direction::Minimize);
|
||||
|
||||
// Trials reporting at rung step=3 (not step=1)
|
||||
let completed: Vec<_> = (0..6)
|
||||
.map(|i| make_trial(i, &[(3, (i + 1) as f64)]))
|
||||
.collect();
|
||||
|
||||
// Current trial reports at step 5 (between rung 3 and rung 9)
|
||||
// Highest rung <= 5 is 3. Use value at rung step 3.
|
||||
// Trial has value at step 3 → use it
|
||||
assert!(!pruner.should_prune(6, 5, &[(3, 2.0)], &completed));
|
||||
assert!(pruner.should_prune(6, 5, &[(3, 5.0)], &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn no_prune_at_max_resource() {
|
||||
let pruner = SuccessiveHalvingPruner::new();
|
||||
let completed: Vec<_> = (0..9)
|
||||
.map(|i| make_trial(i, &[(81, (i + 1) as f64)]))
|
||||
.collect();
|
||||
|
||||
// At the max resource rung, never prune (trial should complete)
|
||||
assert!(!pruner.should_prune(9, 81, &[(81, 100.0)], &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn includes_pruned_trials_in_comparison() {
|
||||
let pruner = SuccessiveHalvingPruner::new().direction(Direction::Minimize);
|
||||
|
||||
// Mix of completed and pruned trials at rung step=1
|
||||
let completed = vec![
|
||||
make_trial(0, &[(1, 1.0)]),
|
||||
make_trial(1, &[(1, 2.0)]),
|
||||
make_pruned_trial(2, &[(1, 8.0)]),
|
||||
make_pruned_trial(3, &[(1, 9.0)]),
|
||||
make_pruned_trial(4, &[(1, 10.0)]),
|
||||
];
|
||||
|
||||
// 6 total. ceil(6/3) = 2 keep. Threshold = 2.0
|
||||
// Value 2.0 → keep
|
||||
assert!(!pruner.should_prune(5, 1, &[(1, 2.0)], &completed));
|
||||
// Value 3.0 → prune
|
||||
assert!(pruner.should_prune(5, 1, &[(1, 3.0)], &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
#[should_panic(expected = "min_resource must be > 0")]
|
||||
fn rejects_zero_min_resource() {
|
||||
let _ = SuccessiveHalvingPruner::new().min_resource(0);
|
||||
}
|
||||
|
||||
#[test]
|
||||
#[should_panic(expected = "max_resource must be > 0")]
|
||||
fn rejects_zero_max_resource() {
|
||||
let _ = SuccessiveHalvingPruner::new().max_resource(0);
|
||||
}
|
||||
|
||||
#[test]
|
||||
#[should_panic(expected = "reduction_factor must be >= 2")]
|
||||
fn rejects_reduction_factor_one() {
|
||||
let _ = SuccessiveHalvingPruner::new().reduction_factor(1);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,83 @@
|
||||
use super::Pruner;
|
||||
use crate::sampler::CompletedTrial;
|
||||
|
||||
/// Prune trials whose intermediate values exceed fixed thresholds.
|
||||
///
|
||||
/// Useful for cutting off trials that are clearly diverging or stuck
|
||||
/// at bad values early in training.
|
||||
///
|
||||
/// # Examples
|
||||
///
|
||||
/// ```
|
||||
/// use optimizer::pruner::ThresholdPruner;
|
||||
///
|
||||
/// // Prune if the intermediate value exceeds 100.0 or falls below 0.0
|
||||
/// let pruner = ThresholdPruner::new().upper(100.0).lower(0.0);
|
||||
/// ```
|
||||
pub struct ThresholdPruner {
|
||||
/// Prune if intermediate value is greater than this. `None` = no upper bound.
|
||||
upper: Option<f64>,
|
||||
/// Prune if intermediate value is less than this. `None` = no lower bound.
|
||||
lower: Option<f64>,
|
||||
}
|
||||
|
||||
impl ThresholdPruner {
|
||||
/// Create a new `ThresholdPruner` with no thresholds set.
|
||||
///
|
||||
/// By default, no pruning occurs. Use [`upper`](Self::upper) and
|
||||
/// [`lower`](Self::lower) to set bounds.
|
||||
#[must_use]
|
||||
pub fn new() -> Self {
|
||||
Self {
|
||||
upper: None,
|
||||
lower: None,
|
||||
}
|
||||
}
|
||||
|
||||
/// Set the upper threshold. Trials with intermediate values above this
|
||||
/// will be pruned.
|
||||
#[must_use]
|
||||
pub fn upper(mut self, threshold: f64) -> Self {
|
||||
self.upper = Some(threshold);
|
||||
self
|
||||
}
|
||||
|
||||
/// Set the lower threshold. Trials with intermediate values below this
|
||||
/// will be pruned.
|
||||
#[must_use]
|
||||
pub fn lower(mut self, threshold: f64) -> Self {
|
||||
self.lower = Some(threshold);
|
||||
self
|
||||
}
|
||||
}
|
||||
|
||||
impl Default for ThresholdPruner {
|
||||
fn default() -> Self {
|
||||
Self::new()
|
||||
}
|
||||
}
|
||||
|
||||
impl Pruner for ThresholdPruner {
|
||||
fn should_prune(
|
||||
&self,
|
||||
_trial_id: u64,
|
||||
_step: u64,
|
||||
intermediate_values: &[(u64, f64)],
|
||||
_completed_trials: &[CompletedTrial],
|
||||
) -> bool {
|
||||
let Some(&(_, latest_value)) = intermediate_values.last() else {
|
||||
return false;
|
||||
};
|
||||
if let Some(upper) = self.upper
|
||||
&& latest_value > upper
|
||||
{
|
||||
return true;
|
||||
}
|
||||
if let Some(lower) = self.lower
|
||||
&& latest_value < lower
|
||||
{
|
||||
return true;
|
||||
}
|
||||
false
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,531 @@
|
||||
use core::cmp::Ordering;
|
||||
|
||||
use super::Pruner;
|
||||
use crate::sampler::CompletedTrial;
|
||||
use crate::types::{Direction, TrialState};
|
||||
|
||||
/// Prune trials using a Wilcoxon signed-rank test comparing intermediate
|
||||
/// values against the best completed trial.
|
||||
///
|
||||
/// More principled than `MedianPruner` for noisy objectives — it accounts
|
||||
/// for the paired nature of step-aligned comparisons and doesn't prune
|
||||
/// on random fluctuations.
|
||||
///
|
||||
/// The test compares intermediate values at matching steps between the
|
||||
/// current trial and the best completed trial. If the current trial is
|
||||
/// statistically significantly worse (p < threshold), it is pruned.
|
||||
///
|
||||
/// # Examples
|
||||
///
|
||||
/// ```
|
||||
/// use optimizer::Direction;
|
||||
/// use optimizer::pruner::WilcoxonPruner;
|
||||
///
|
||||
/// let pruner = WilcoxonPruner::new(Direction::Minimize)
|
||||
/// .p_value_threshold(0.05)
|
||||
/// .n_warmup_steps(5)
|
||||
/// .n_min_trials(1);
|
||||
/// ```
|
||||
pub struct WilcoxonPruner {
|
||||
/// Significance level (default 0.05). Lower = more conservative.
|
||||
p_value_threshold: f64,
|
||||
/// Don't prune in the first N steps (let the trial warm up).
|
||||
n_warmup_steps: u64,
|
||||
/// Require at least N completed trials before pruning.
|
||||
n_min_trials: usize,
|
||||
/// The optimization direction.
|
||||
direction: Direction,
|
||||
}
|
||||
|
||||
impl WilcoxonPruner {
|
||||
/// Create a new `WilcoxonPruner` for the given optimization direction.
|
||||
///
|
||||
/// By default, `p_value_threshold` is 0.05, `n_warmup_steps` is 0,
|
||||
/// and `n_min_trials` is 1.
|
||||
#[must_use]
|
||||
pub fn new(direction: Direction) -> Self {
|
||||
Self {
|
||||
p_value_threshold: 0.05,
|
||||
n_warmup_steps: 0,
|
||||
n_min_trials: 1,
|
||||
direction,
|
||||
}
|
||||
}
|
||||
|
||||
/// Set the p-value threshold for significance.
|
||||
///
|
||||
/// Must be in (0.0, 1.0). Lower values are more conservative (harder to prune).
|
||||
///
|
||||
/// # Panics
|
||||
///
|
||||
/// Panics if `p` is not in the open interval (0.0, 1.0).
|
||||
#[must_use]
|
||||
pub fn p_value_threshold(mut self, p: f64) -> Self {
|
||||
assert!(
|
||||
p > 0.0 && p < 1.0,
|
||||
"p_value_threshold must be in (0.0, 1.0)"
|
||||
);
|
||||
self.p_value_threshold = p;
|
||||
self
|
||||
}
|
||||
|
||||
/// Set the number of warmup steps. No pruning occurs before this step.
|
||||
#[must_use]
|
||||
pub fn n_warmup_steps(mut self, n: u64) -> Self {
|
||||
self.n_warmup_steps = n;
|
||||
self
|
||||
}
|
||||
|
||||
/// Set the minimum number of completed trials required before pruning.
|
||||
#[must_use]
|
||||
pub fn n_min_trials(mut self, n: usize) -> Self {
|
||||
self.n_min_trials = n;
|
||||
self
|
||||
}
|
||||
}
|
||||
|
||||
impl Pruner for WilcoxonPruner {
|
||||
fn should_prune(
|
||||
&self,
|
||||
_trial_id: u64,
|
||||
step: u64,
|
||||
intermediate_values: &[(u64, f64)],
|
||||
completed_trials: &[CompletedTrial],
|
||||
) -> bool {
|
||||
if step < self.n_warmup_steps {
|
||||
return false;
|
||||
}
|
||||
|
||||
let completed: Vec<&CompletedTrial> = completed_trials
|
||||
.iter()
|
||||
.filter(|t| t.state == TrialState::Complete)
|
||||
.collect();
|
||||
|
||||
if completed.len() < self.n_min_trials {
|
||||
return false;
|
||||
}
|
||||
|
||||
// Find the best completed trial by final objective value.
|
||||
let best = match self.direction {
|
||||
Direction::Minimize => completed
|
||||
.iter()
|
||||
.min_by(|a, b| a.value.partial_cmp(&b.value).unwrap_or(Ordering::Equal)),
|
||||
Direction::Maximize => completed
|
||||
.iter()
|
||||
.max_by(|a, b| a.value.partial_cmp(&b.value).unwrap_or(Ordering::Equal)),
|
||||
};
|
||||
|
||||
let Some(best) = best else {
|
||||
return false;
|
||||
};
|
||||
|
||||
// Pair intermediate values at matching steps.
|
||||
let pairs: Vec<(f64, f64)> = intermediate_values
|
||||
.iter()
|
||||
.filter_map(|&(s, current_v)| {
|
||||
best.intermediate_values
|
||||
.iter()
|
||||
.find(|(bs, _)| *bs == s)
|
||||
.map(|&(_, best_v)| (current_v, best_v))
|
||||
})
|
||||
.collect();
|
||||
|
||||
// Need at least 6 pairs for a meaningful test.
|
||||
if pairs.len() < 6 {
|
||||
return false;
|
||||
}
|
||||
|
||||
// Compute signed differences: current - best.
|
||||
// For minimization: positive diff means current is worse.
|
||||
// For maximization: negative diff means current is worse.
|
||||
let differences: Vec<f64> = pairs
|
||||
.iter()
|
||||
.map(|&(current, best_v)| current - best_v)
|
||||
.collect();
|
||||
|
||||
// Run the Wilcoxon signed-rank test.
|
||||
let p_value = wilcoxon_signed_rank_test(&differences, self.direction);
|
||||
|
||||
p_value < self.p_value_threshold
|
||||
}
|
||||
}
|
||||
|
||||
/// Perform a one-sided Wilcoxon signed-rank test.
|
||||
///
|
||||
/// Tests whether the values tend to be worse than zero (positive for
|
||||
/// minimization, negative for maximization).
|
||||
///
|
||||
/// Returns a p-value. Small p-values indicate the current trial is
|
||||
/// significantly worse.
|
||||
fn wilcoxon_signed_rank_test(differences: &[f64], direction: Direction) -> f64 {
|
||||
// 1. Remove zero differences.
|
||||
let nonzero: Vec<f64> = differences.iter().copied().filter(|d| *d != 0.0).collect();
|
||||
let n = nonzero.len();
|
||||
|
||||
if n < 6 {
|
||||
return 1.0; // Not enough data
|
||||
}
|
||||
|
||||
// 2. Rank by absolute value.
|
||||
let mut abs_ranked: Vec<(usize, f64, f64)> = nonzero
|
||||
.iter()
|
||||
.enumerate()
|
||||
.map(|(i, &d)| (i, d.abs(), d))
|
||||
.collect();
|
||||
abs_ranked.sort_by(|a, b| a.1.partial_cmp(&b.1).unwrap_or(Ordering::Equal));
|
||||
|
||||
// 3. Assign ranks with tie correction.
|
||||
let ranks = assign_ranks(&abs_ranked);
|
||||
|
||||
// 4. Compute W+ (sum of ranks for positive differences) and
|
||||
// W- (sum of ranks for negative differences).
|
||||
let mut w_plus = 0.0;
|
||||
let mut w_minus = 0.0;
|
||||
for (i, &(_, _, orig)) in abs_ranked.iter().enumerate() {
|
||||
if orig > 0.0 {
|
||||
w_plus += ranks[i];
|
||||
} else {
|
||||
w_minus += ranks[i];
|
||||
}
|
||||
}
|
||||
|
||||
// For one-sided test:
|
||||
// - Minimization: we want to detect positive diffs (current worse).
|
||||
// Large W+ means significantly worse. Test statistic = W-.
|
||||
// - Maximization: we want to detect negative diffs (current worse).
|
||||
// Large W- means significantly worse. Test statistic = W+.
|
||||
let w = match direction {
|
||||
Direction::Minimize => w_minus,
|
||||
Direction::Maximize => w_plus,
|
||||
};
|
||||
|
||||
// 5. Normal approximation for the p-value.
|
||||
#[allow(clippy::cast_precision_loss)]
|
||||
let n_f = n as f64;
|
||||
let mean = n_f * (n_f + 1.0) / 4.0;
|
||||
let variance = n_f * (n_f + 1.0) * (2.0 * n_f + 1.0) / 24.0;
|
||||
|
||||
// Tie correction for variance.
|
||||
let tie_correction = compute_tie_correction(&ranks);
|
||||
let adjusted_variance = variance - tie_correction;
|
||||
|
||||
if adjusted_variance <= 0.0 {
|
||||
return 1.0;
|
||||
}
|
||||
|
||||
let std_dev = adjusted_variance.sqrt();
|
||||
|
||||
// Continuity correction: shift W by 0.5 towards mean.
|
||||
let continuity = if w < mean { 0.5 } else { -0.5 };
|
||||
let z = (w + continuity - mean) / std_dev;
|
||||
|
||||
// One-sided p-value (lower tail): probability that the test statistic
|
||||
// is this small or smaller under H0.
|
||||
normal_cdf(z)
|
||||
}
|
||||
|
||||
/// Assign average ranks, handling ties.
|
||||
fn assign_ranks(sorted: &[(usize, f64, f64)]) -> Vec<f64> {
|
||||
let n = sorted.len();
|
||||
let mut ranks = vec![0.0; n];
|
||||
let mut i = 0;
|
||||
|
||||
while i < n {
|
||||
let mut j = i;
|
||||
// Find all items tied with sorted[i].
|
||||
while j < n
|
||||
&& (sorted[j].1 - sorted[i].1).abs() < f64::EPSILON * sorted[i].1.max(1.0) * 100.0
|
||||
{
|
||||
j += 1;
|
||||
}
|
||||
// Average rank for the tie group. Ranks are 1-based.
|
||||
#[allow(clippy::cast_precision_loss)]
|
||||
let avg_rank = (i + 1 + j) as f64 / 2.0;
|
||||
for rank in ranks.iter_mut().take(j).skip(i) {
|
||||
*rank = avg_rank;
|
||||
}
|
||||
i = j;
|
||||
}
|
||||
|
||||
ranks
|
||||
}
|
||||
|
||||
/// Compute the tie correction term for the variance.
|
||||
/// For each tie group of size t, subtract t^3 - t from the sum,
|
||||
/// then divide by 48.
|
||||
fn compute_tie_correction(ranks: &[f64]) -> f64 {
|
||||
let mut correction = 0.0;
|
||||
let mut i = 0;
|
||||
|
||||
while i < ranks.len() {
|
||||
let mut j = i;
|
||||
while j < ranks.len() && (ranks[j] - ranks[i]).abs() < f64::EPSILON {
|
||||
j += 1;
|
||||
}
|
||||
#[allow(clippy::cast_precision_loss)]
|
||||
let t = (j - i) as f64;
|
||||
if t > 1.0 {
|
||||
correction += t * t * t - t;
|
||||
}
|
||||
i = j;
|
||||
}
|
||||
|
||||
correction / 48.0
|
||||
}
|
||||
|
||||
/// Standard normal CDF using an approximation (Abramowitz & Stegun).
|
||||
fn normal_cdf(x: f64) -> f64 {
|
||||
// Use the complementary error function relationship:
|
||||
// Φ(x) = 0.5 * erfc(-x / √2)
|
||||
0.5 * erfc(-x / core::f64::consts::SQRT_2)
|
||||
}
|
||||
|
||||
/// Complementary error function approximation.
|
||||
/// Maximum error: 1.5 × 10⁻⁷ (Abramowitz & Stegun formula 7.1.26).
|
||||
fn erfc(x: f64) -> f64 {
|
||||
let t = 1.0 / (1.0 + 0.327_591_1 * x.abs());
|
||||
let poly = t
|
||||
* (0.254_829_592
|
||||
+ t * (-0.284_496_736
|
||||
+ t * (1.421_413_741 + t * (-1.453_152_027 + t * 1.061_405_429))));
|
||||
let result = poly * (-x * x).exp();
|
||||
|
||||
if x >= 0.0 { result } else { 2.0 - result }
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use std::collections::HashMap;
|
||||
|
||||
use super::*;
|
||||
|
||||
fn trial_with_values(
|
||||
id: u64,
|
||||
value: f64,
|
||||
intermediate_values: Vec<(u64, f64)>,
|
||||
) -> CompletedTrial {
|
||||
CompletedTrial::with_intermediate_values(
|
||||
id,
|
||||
HashMap::new(),
|
||||
HashMap::new(),
|
||||
HashMap::new(),
|
||||
value,
|
||||
intermediate_values,
|
||||
HashMap::new(),
|
||||
)
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn no_prune_during_warmup() {
|
||||
let pruner = WilcoxonPruner::new(Direction::Minimize).n_warmup_steps(10);
|
||||
let completed = vec![trial_with_values(
|
||||
0,
|
||||
0.1,
|
||||
(0..20).map(|s| (s, 0.1)).collect(),
|
||||
)];
|
||||
let current: Vec<(u64, f64)> = (0..8).map(|s| (s, 100.0)).collect();
|
||||
assert!(!pruner.should_prune(1, 7, ¤t, &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn no_prune_with_insufficient_trials() {
|
||||
let pruner = WilcoxonPruner::new(Direction::Minimize).n_min_trials(5);
|
||||
let completed = vec![trial_with_values(
|
||||
0,
|
||||
0.1,
|
||||
(0..20).map(|s| (s, 0.1)).collect(),
|
||||
)];
|
||||
let current: Vec<(u64, f64)> = (0..10).map(|s| (s, 100.0)).collect();
|
||||
assert!(!pruner.should_prune(1, 9, ¤t, &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn no_prune_with_fewer_than_6_pairs() {
|
||||
let pruner = WilcoxonPruner::new(Direction::Minimize);
|
||||
let completed = vec![trial_with_values(
|
||||
0,
|
||||
0.1,
|
||||
(0..5).map(|s| (s, 0.1)).collect(),
|
||||
)];
|
||||
// Only 5 matching steps
|
||||
let current: Vec<(u64, f64)> = (0..5).map(|s| (s, 100.0)).collect();
|
||||
assert!(!pruner.should_prune(1, 4, ¤t, &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn prune_when_consistently_worse_minimize() {
|
||||
let pruner = WilcoxonPruner::new(Direction::Minimize);
|
||||
|
||||
// Best trial has low values.
|
||||
let best_values: Vec<(u64, f64)> = (0..20).map(|s| (s, 0.1)).collect();
|
||||
let completed = vec![trial_with_values(0, 0.1, best_values)];
|
||||
|
||||
// Current trial is consistently much worse.
|
||||
let current: Vec<(u64, f64)> = (0..20).map(|s| (s, 10.0)).collect();
|
||||
assert!(pruner.should_prune(1, 19, ¤t, &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn prune_when_consistently_worse_maximize() {
|
||||
let pruner = WilcoxonPruner::new(Direction::Maximize);
|
||||
|
||||
// Best trial has high values.
|
||||
let best_values: Vec<(u64, f64)> = (0..20).map(|s| (s, 10.0)).collect();
|
||||
let completed = vec![trial_with_values(0, 10.0, best_values)];
|
||||
|
||||
// Current trial is consistently much worse.
|
||||
let current: Vec<(u64, f64)> = (0..20).map(|s| (s, 0.1)).collect();
|
||||
assert!(pruner.should_prune(1, 19, ¤t, &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn no_prune_when_statistically_similar() {
|
||||
let pruner = WilcoxonPruner::new(Direction::Minimize);
|
||||
|
||||
// Best trial and current trial have very similar values with noise.
|
||||
let best_values: Vec<(u64, f64)> = (0..20_u64)
|
||||
.map(|s| {
|
||||
let noise = if s.is_multiple_of(2) { 0.01 } else { -0.01 };
|
||||
(s, 1.0 + noise)
|
||||
})
|
||||
.collect();
|
||||
let completed = vec![trial_with_values(0, 1.0, best_values)];
|
||||
|
||||
// Current trial is similar — alternating above/below.
|
||||
let current: Vec<(u64, f64)> = (0..20_u64)
|
||||
.map(|s| {
|
||||
let noise = if s.is_multiple_of(2) { -0.01 } else { 0.01 };
|
||||
(s, 1.0 + noise)
|
||||
})
|
||||
.collect();
|
||||
assert!(!pruner.should_prune(1, 19, ¤t, &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn selects_best_trial_minimize() {
|
||||
let pruner = WilcoxonPruner::new(Direction::Minimize);
|
||||
|
||||
// Two completed trials: trial 0 is better (lower).
|
||||
let completed = vec![
|
||||
trial_with_values(0, 0.1, (0..20).map(|s| (s, 0.1)).collect()),
|
||||
trial_with_values(1, 5.0, (0..20).map(|s| (s, 5.0)).collect()),
|
||||
];
|
||||
|
||||
// Current trial is worse than the best but similar to the second.
|
||||
let current: Vec<(u64, f64)> = (0..20).map(|s| (s, 5.0)).collect();
|
||||
assert!(pruner.should_prune(2, 19, ¤t, &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn selects_best_trial_maximize() {
|
||||
let pruner = WilcoxonPruner::new(Direction::Maximize);
|
||||
|
||||
// Two completed trials: trial 1 is better (higher).
|
||||
let completed = vec![
|
||||
trial_with_values(0, 0.1, (0..20).map(|s| (s, 0.1)).collect()),
|
||||
trial_with_values(1, 10.0, (0..20).map(|s| (s, 10.0)).collect()),
|
||||
];
|
||||
|
||||
// Current trial is worse than the best.
|
||||
let current: Vec<(u64, f64)> = (0..20).map(|s| (s, 0.1)).collect();
|
||||
assert!(pruner.should_prune(2, 19, ¤t, &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn ignores_pruned_trials() {
|
||||
let pruner = WilcoxonPruner::new(Direction::Minimize);
|
||||
|
||||
// Only a pruned trial — no complete trials.
|
||||
let mut trial = trial_with_values(0, 0.1, (0..20).map(|s| (s, 0.1)).collect());
|
||||
trial.state = TrialState::Pruned;
|
||||
let completed = vec![trial];
|
||||
|
||||
let current: Vec<(u64, f64)> = (0..20).map(|s| (s, 100.0)).collect();
|
||||
assert!(!pruner.should_prune(1, 19, ¤t, &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn lower_p_value_is_more_conservative() {
|
||||
let strict = WilcoxonPruner::new(Direction::Minimize).p_value_threshold(0.001);
|
||||
let lenient = WilcoxonPruner::new(Direction::Minimize).p_value_threshold(0.1);
|
||||
|
||||
let completed = vec![trial_with_values(
|
||||
0,
|
||||
0.1,
|
||||
(0..20).map(|s| (s, 0.1)).collect(),
|
||||
)];
|
||||
|
||||
// Moderately worse — should pass lenient but maybe not strict.
|
||||
let current: Vec<(u64, f64)> = (0..20)
|
||||
.map(|s| if s < 15 { (s, 0.2) } else { (s, 0.15) })
|
||||
.collect();
|
||||
|
||||
let lenient_prunes = lenient.should_prune(1, 19, ¤t, &completed);
|
||||
let strict_prunes = strict.should_prune(1, 19, ¤t, &completed);
|
||||
|
||||
// A stricter threshold should never prune when a lenient one doesn't.
|
||||
if !lenient_prunes {
|
||||
assert!(!strict_prunes);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
#[should_panic(expected = "p_value_threshold must be in (0.0, 1.0)")]
|
||||
fn panics_on_zero_p_value() {
|
||||
let _ = WilcoxonPruner::new(Direction::Minimize).p_value_threshold(0.0);
|
||||
}
|
||||
|
||||
#[test]
|
||||
#[should_panic(expected = "p_value_threshold must be in (0.0, 1.0)")]
|
||||
fn panics_on_one_p_value() {
|
||||
let _ = WilcoxonPruner::new(Direction::Minimize).p_value_threshold(1.0);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn correct_signed_rank_statistic() {
|
||||
// Known example: differences [1, 2, 3, 4, 5, 6] (all positive).
|
||||
// Ranks: 1, 2, 3, 4, 5, 6. W+ = 21, W- = 0.
|
||||
// For minimization (testing if positive = worse), W- = 0.
|
||||
// This should give a very small p-value.
|
||||
let diffs = vec![1.0, 2.0, 3.0, 4.0, 5.0, 6.0];
|
||||
let p = wilcoxon_signed_rank_test(&diffs, Direction::Minimize);
|
||||
assert!(
|
||||
p < 0.05,
|
||||
"p-value {p} should be < 0.05 for all-positive diffs"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn symmetric_differences_not_significant() {
|
||||
// Balanced differences: half positive, half negative.
|
||||
let diffs = vec![1.0, -1.0, 2.0, -2.0, 3.0, -3.0, 4.0, -4.0];
|
||||
let p = wilcoxon_signed_rank_test(&diffs, Direction::Minimize);
|
||||
assert!(p > 0.05, "p-value {p} should be > 0.05 for symmetric diffs");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn normal_cdf_known_values() {
|
||||
assert!((normal_cdf(0.0) - 0.5).abs() < 1e-6);
|
||||
assert!(normal_cdf(-10.0) < 1e-6);
|
||||
assert!((normal_cdf(10.0) - 1.0).abs() < 1e-6);
|
||||
assert!((normal_cdf(-1.96) - 0.025).abs() < 0.001);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn no_intermediate_values() {
|
||||
let pruner = WilcoxonPruner::new(Direction::Minimize);
|
||||
let completed = vec![trial_with_values(
|
||||
0,
|
||||
0.1,
|
||||
(0..20).map(|s| (s, 0.1)).collect(),
|
||||
)];
|
||||
assert!(!pruner.should_prune(1, 0, &[], &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn no_completed_trials() {
|
||||
let pruner = WilcoxonPruner::new(Direction::Minimize);
|
||||
let current: Vec<(u64, f64)> = (0..20).map(|s| (s, 1.0)).collect();
|
||||
assert!(!pruner.should_prune(1, 19, ¤t, &[]));
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,691 @@
|
||||
//! BOHB (Bayesian Optimization + `HyperBand`) sampler.
|
||||
//!
|
||||
//! BOHB combines TPE's model-guided sampling with Hyperband's budget-aware
|
||||
//! evaluation. Instead of building one global TPE model, BOHB conditions
|
||||
//! its TPE model on trials evaluated at a specific budget level, giving
|
||||
//! better-calibrated proposals for each rung of the Hyperband schedule.
|
||||
//!
|
||||
//! # How it works
|
||||
//!
|
||||
//! 1. Compute all Hyperband rung steps (budget levels) from the config.
|
||||
//! 2. On each `sample()` call, scan the history's `intermediate_values`
|
||||
//! to find the **largest budget level** with enough observations
|
||||
//! (`>= min_points_in_model`).
|
||||
//! 3. Build a filtered history where each trial's `value` is replaced
|
||||
//! with its intermediate value at that budget level.
|
||||
//! 4. Delegate to an internal [`TpeSampler`] for the actual sampling.
|
||||
//! 5. Fall back to random sampling if no budget level has enough data.
|
||||
//!
|
||||
//! # Examples
|
||||
//!
|
||||
//! ```
|
||||
//! use optimizer::sampler::bohb::BohbSampler;
|
||||
//! use optimizer::{Direction, Study};
|
||||
//!
|
||||
//! let bohb = BohbSampler::new();
|
||||
//! let pruner = bohb.matching_pruner(Direction::Minimize);
|
||||
//! let study: Study<f64> = Study::with_sampler_and_pruner(Direction::Minimize, bohb, pruner);
|
||||
//! ```
|
||||
//!
|
||||
//! Using the builder for custom configuration:
|
||||
//!
|
||||
//! ```
|
||||
//! use optimizer::sampler::bohb::BohbSampler;
|
||||
//!
|
||||
//! let bohb = BohbSampler::builder()
|
||||
//! .min_resource(1)
|
||||
//! .max_resource(81)
|
||||
//! .reduction_factor(3)
|
||||
//! .min_points_in_model(10)
|
||||
//! .seed(42)
|
||||
//! .build()
|
||||
//! .unwrap();
|
||||
//! ```
|
||||
|
||||
use crate::distribution::Distribution;
|
||||
use crate::error::Result;
|
||||
use crate::param::ParamValue;
|
||||
use crate::pruner::HyperbandPruner;
|
||||
use crate::sampler::tpe::TpeSampler;
|
||||
use crate::sampler::{CompletedTrial, Sampler};
|
||||
use crate::types::Direction;
|
||||
|
||||
/// A BOHB sampler that combines TPE with Hyperband budget awareness.
|
||||
///
|
||||
/// BOHB filters trial history by budget level before delegating to TPE,
|
||||
/// so the surrogate model is conditioned on trials evaluated at the same
|
||||
/// resource level. This produces better-calibrated parameter proposals
|
||||
/// than using a single global model across all budgets.
|
||||
///
|
||||
/// Use [`BohbSampler::matching_pruner`] to create a [`HyperbandPruner`]
|
||||
/// with matching parameters.
|
||||
pub struct BohbSampler {
|
||||
min_resource: u64,
|
||||
max_resource: u64,
|
||||
reduction_factor: u64,
|
||||
min_points_in_model: usize,
|
||||
tpe: TpeSampler,
|
||||
}
|
||||
|
||||
impl BohbSampler {
|
||||
/// Creates a new BOHB sampler with default settings.
|
||||
///
|
||||
/// Defaults:
|
||||
/// - `min_resource`: 1
|
||||
/// - `max_resource`: 81
|
||||
/// - `reduction_factor`: 3
|
||||
/// - `min_points_in_model`: 10
|
||||
/// - TPE: default settings
|
||||
#[must_use]
|
||||
pub fn new() -> Self {
|
||||
Self {
|
||||
min_resource: 1,
|
||||
max_resource: 81,
|
||||
reduction_factor: 3,
|
||||
min_points_in_model: 10,
|
||||
tpe: TpeSampler::new(),
|
||||
}
|
||||
}
|
||||
|
||||
/// Creates a builder for configuring a BOHB sampler.
|
||||
///
|
||||
/// # Examples
|
||||
///
|
||||
/// ```
|
||||
/// use optimizer::sampler::bohb::BohbSampler;
|
||||
///
|
||||
/// let sampler = BohbSampler::builder()
|
||||
/// .min_resource(1)
|
||||
/// .max_resource(27)
|
||||
/// .reduction_factor(3)
|
||||
/// .min_points_in_model(5)
|
||||
/// .seed(42)
|
||||
/// .build()
|
||||
/// .unwrap();
|
||||
/// ```
|
||||
#[must_use]
|
||||
pub fn builder() -> BohbSamplerBuilder {
|
||||
BohbSamplerBuilder::new()
|
||||
}
|
||||
|
||||
/// Creates a [`HyperbandPruner`] with matching Hyperband parameters.
|
||||
///
|
||||
/// This ensures the pruner's budget schedule is consistent with the
|
||||
/// budget levels used by BOHB for model conditioning.
|
||||
#[must_use]
|
||||
pub fn matching_pruner(&self, direction: Direction) -> HyperbandPruner {
|
||||
HyperbandPruner::new()
|
||||
.min_resource(self.min_resource)
|
||||
.max_resource(self.max_resource)
|
||||
.reduction_factor(self.reduction_factor)
|
||||
.direction(direction)
|
||||
}
|
||||
|
||||
/// Compute all unique budget levels (rung steps) across all Hyperband brackets.
|
||||
///
|
||||
/// Returns sorted ascending.
|
||||
#[allow(
|
||||
clippy::cast_precision_loss,
|
||||
clippy::cast_possible_truncation,
|
||||
clippy::cast_sign_loss
|
||||
)]
|
||||
fn all_budget_levels(&self) -> Vec<u64> {
|
||||
let eta = self.reduction_factor as f64;
|
||||
let ratio = self.max_resource as f64 / self.min_resource as f64;
|
||||
let s_max = (ratio.ln() / eta.ln()).floor() as u64;
|
||||
|
||||
let mut levels = Vec::new();
|
||||
for bracket in 0..=s_max {
|
||||
let exponent = s_max.saturating_sub(bracket);
|
||||
let min_resource_bracket =
|
||||
(self.max_resource as f64 / eta.powi(exponent as i32)).ceil() as u64;
|
||||
|
||||
let mut rung: u32 = 0;
|
||||
while let Some(power) = self.reduction_factor.checked_pow(rung) {
|
||||
let step = min_resource_bracket.saturating_mul(power);
|
||||
if step > self.max_resource {
|
||||
break;
|
||||
}
|
||||
levels.push(step);
|
||||
rung += 1;
|
||||
}
|
||||
}
|
||||
|
||||
levels.sort_unstable();
|
||||
levels.dedup();
|
||||
levels
|
||||
}
|
||||
|
||||
/// Build a filtered history for a specific budget level.
|
||||
///
|
||||
/// For each trial that has an intermediate value at the given budget step,
|
||||
/// creates a new `CompletedTrial` with `value` replaced by the intermediate
|
||||
/// value at that step.
|
||||
fn filter_history_for_budget(history: &[CompletedTrial], budget: u64) -> Vec<CompletedTrial> {
|
||||
history
|
||||
.iter()
|
||||
.filter_map(|trial| {
|
||||
trial
|
||||
.intermediate_values
|
||||
.iter()
|
||||
.find(|(step, _)| *step == budget)
|
||||
.map(|(_, iv)| CompletedTrial {
|
||||
id: trial.id,
|
||||
params: trial.params.clone(),
|
||||
distributions: trial.distributions.clone(),
|
||||
param_labels: trial.param_labels.clone(),
|
||||
value: *iv,
|
||||
intermediate_values: trial.intermediate_values.clone(),
|
||||
state: trial.state,
|
||||
user_attrs: trial.user_attrs.clone(),
|
||||
constraints: trial.constraints.clone(),
|
||||
})
|
||||
})
|
||||
.collect()
|
||||
}
|
||||
}
|
||||
|
||||
impl Default for BohbSampler {
|
||||
fn default() -> Self {
|
||||
Self::new()
|
||||
}
|
||||
}
|
||||
|
||||
impl Sampler for BohbSampler {
|
||||
fn sample(
|
||||
&self,
|
||||
distribution: &Distribution,
|
||||
trial_id: u64,
|
||||
history: &[CompletedTrial],
|
||||
) -> ParamValue {
|
||||
// Find the largest budget level with enough observations
|
||||
let levels = self.all_budget_levels();
|
||||
|
||||
for &budget in levels.iter().rev() {
|
||||
let count = history
|
||||
.iter()
|
||||
.filter(|t| {
|
||||
t.intermediate_values
|
||||
.iter()
|
||||
.any(|(step, _)| *step == budget)
|
||||
})
|
||||
.count();
|
||||
|
||||
if count >= self.min_points_in_model {
|
||||
let filtered = Self::filter_history_for_budget(history, budget);
|
||||
return self.tpe.sample(distribution, trial_id, &filtered);
|
||||
}
|
||||
}
|
||||
|
||||
// Not enough data at any budget level: delegate to TPE with empty history
|
||||
// which triggers its uniform-random startup behavior.
|
||||
self.tpe.sample(distribution, trial_id, &[])
|
||||
}
|
||||
}
|
||||
|
||||
/// Builder for configuring a [`BohbSampler`].
|
||||
///
|
||||
/// # Examples
|
||||
///
|
||||
/// ```
|
||||
/// use optimizer::sampler::bohb::BohbSamplerBuilder;
|
||||
///
|
||||
/// let sampler = BohbSamplerBuilder::new()
|
||||
/// .min_resource(1)
|
||||
/// .max_resource(81)
|
||||
/// .reduction_factor(3)
|
||||
/// .gamma(0.15)
|
||||
/// .seed(42)
|
||||
/// .build()
|
||||
/// .unwrap();
|
||||
/// ```
|
||||
pub struct BohbSamplerBuilder {
|
||||
min_resource: u64,
|
||||
max_resource: u64,
|
||||
reduction_factor: u64,
|
||||
min_points_in_model: usize,
|
||||
tpe_builder: crate::sampler::tpe::TpeSamplerBuilder,
|
||||
}
|
||||
|
||||
impl BohbSamplerBuilder {
|
||||
/// Creates a new builder with default settings.
|
||||
#[must_use]
|
||||
pub fn new() -> Self {
|
||||
Self {
|
||||
min_resource: 1,
|
||||
max_resource: 81,
|
||||
reduction_factor: 3,
|
||||
min_points_in_model: 10,
|
||||
tpe_builder: crate::sampler::tpe::TpeSamplerBuilder::new(),
|
||||
}
|
||||
}
|
||||
|
||||
/// Sets the minimum resource (budget) per trial.
|
||||
///
|
||||
/// # Panics
|
||||
///
|
||||
/// Panics if `r` is 0.
|
||||
#[must_use]
|
||||
pub fn min_resource(mut self, r: u64) -> Self {
|
||||
assert!(r > 0, "min_resource must be > 0, got {r}");
|
||||
self.min_resource = r;
|
||||
self
|
||||
}
|
||||
|
||||
/// Sets the maximum resource (budget) per trial.
|
||||
///
|
||||
/// # Panics
|
||||
///
|
||||
/// Panics if `r` is 0.
|
||||
#[must_use]
|
||||
pub fn max_resource(mut self, r: u64) -> Self {
|
||||
assert!(r > 0, "max_resource must be > 0, got {r}");
|
||||
self.max_resource = r;
|
||||
self
|
||||
}
|
||||
|
||||
/// Sets the reduction factor (eta).
|
||||
///
|
||||
/// # Panics
|
||||
///
|
||||
/// Panics if `eta` is less than 2.
|
||||
#[must_use]
|
||||
pub fn reduction_factor(mut self, eta: u64) -> Self {
|
||||
assert!(eta >= 2, "reduction_factor must be >= 2, got {eta}");
|
||||
self.reduction_factor = eta;
|
||||
self
|
||||
}
|
||||
|
||||
/// Sets the minimum number of observations at a budget level before
|
||||
/// BOHB uses TPE instead of random sampling.
|
||||
#[must_use]
|
||||
pub fn min_points_in_model(mut self, n: usize) -> Self {
|
||||
self.min_points_in_model = n;
|
||||
self
|
||||
}
|
||||
|
||||
/// Sets a fixed gamma value for the internal TPE sampler.
|
||||
#[must_use]
|
||||
pub fn gamma(mut self, gamma: f64) -> Self {
|
||||
self.tpe_builder = self.tpe_builder.gamma(gamma);
|
||||
self
|
||||
}
|
||||
|
||||
/// Sets a custom gamma strategy for the internal TPE sampler.
|
||||
#[must_use]
|
||||
pub fn gamma_strategy<G: crate::sampler::tpe::GammaStrategy + 'static>(
|
||||
mut self,
|
||||
strategy: G,
|
||||
) -> Self {
|
||||
self.tpe_builder = self.tpe_builder.gamma_strategy(strategy);
|
||||
self
|
||||
}
|
||||
|
||||
/// Sets the number of EI candidates for the internal TPE sampler.
|
||||
#[must_use]
|
||||
pub fn n_ei_candidates(mut self, n: usize) -> Self {
|
||||
self.tpe_builder = self.tpe_builder.n_ei_candidates(n);
|
||||
self
|
||||
}
|
||||
|
||||
/// Sets a fixed KDE bandwidth for the internal TPE sampler.
|
||||
#[must_use]
|
||||
pub fn kde_bandwidth(mut self, bandwidth: f64) -> Self {
|
||||
self.tpe_builder = self.tpe_builder.kde_bandwidth(bandwidth);
|
||||
self
|
||||
}
|
||||
|
||||
/// Sets a seed for reproducible sampling.
|
||||
#[must_use]
|
||||
pub fn seed(mut self, seed: u64) -> Self {
|
||||
self.tpe_builder = self.tpe_builder.seed(seed);
|
||||
self
|
||||
}
|
||||
|
||||
/// Builds the configured [`BohbSampler`].
|
||||
///
|
||||
/// # Errors
|
||||
///
|
||||
/// Returns an error if the TPE configuration is invalid (e.g. gamma
|
||||
/// not in (0, 1) or bandwidth not positive).
|
||||
pub fn build(self) -> Result<BohbSampler> {
|
||||
let tpe = self.tpe_builder.build()?;
|
||||
Ok(BohbSampler {
|
||||
min_resource: self.min_resource,
|
||||
max_resource: self.max_resource,
|
||||
reduction_factor: self.reduction_factor,
|
||||
min_points_in_model: self.min_points_in_model,
|
||||
tpe,
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
impl Default for BohbSamplerBuilder {
|
||||
fn default() -> Self {
|
||||
Self::new()
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
#[allow(clippy::cast_precision_loss)]
|
||||
mod tests {
|
||||
use std::collections::HashMap;
|
||||
|
||||
use super::*;
|
||||
use crate::distribution::{FloatDistribution, IntDistribution};
|
||||
use crate::parameter::ParamId;
|
||||
use crate::types::TrialState;
|
||||
|
||||
fn make_trial_with_intermediates(
|
||||
id: u64,
|
||||
value: f64,
|
||||
params: Vec<(ParamId, ParamValue, Distribution)>,
|
||||
intermediate_values: Vec<(u64, f64)>,
|
||||
) -> CompletedTrial {
|
||||
let mut param_map = HashMap::new();
|
||||
let mut dist_map = HashMap::new();
|
||||
for (param_id, pv, dist) in params {
|
||||
param_map.insert(param_id, pv);
|
||||
dist_map.insert(param_id, dist);
|
||||
}
|
||||
CompletedTrial {
|
||||
id,
|
||||
params: param_map,
|
||||
distributions: dist_map,
|
||||
param_labels: HashMap::new(),
|
||||
value,
|
||||
intermediate_values,
|
||||
state: TrialState::Complete,
|
||||
user_attrs: HashMap::new(),
|
||||
constraints: Vec::new(),
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn budget_levels_default() {
|
||||
let bohb = BohbSampler::new();
|
||||
let levels = bohb.all_budget_levels();
|
||||
// With min=1, max=81, eta=3:
|
||||
// bracket 0: 1, 3, 9, 27, 81
|
||||
// bracket 1: 3, 9, 27, 81
|
||||
// bracket 2: 9, 27, 81
|
||||
// bracket 3: 27, 81
|
||||
// bracket 4: 81
|
||||
// Unique sorted: [1, 3, 9, 27, 81]
|
||||
assert_eq!(levels, vec![1, 3, 9, 27, 81]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn budget_levels_eta2() {
|
||||
let bohb = BohbSampler::builder()
|
||||
.min_resource(1)
|
||||
.max_resource(16)
|
||||
.reduction_factor(2)
|
||||
.build()
|
||||
.unwrap();
|
||||
let levels = bohb.all_budget_levels();
|
||||
// s_max = floor(ln(16)/ln(2)) = 4
|
||||
// bracket 0: 1, 2, 4, 8, 16
|
||||
// bracket 1: 2, 4, 8, 16
|
||||
// bracket 2: 4, 8, 16
|
||||
// bracket 3: 8, 16
|
||||
// bracket 4: 16
|
||||
// Unique sorted: [1, 2, 4, 8, 16]
|
||||
assert_eq!(levels, vec![1, 2, 4, 8, 16]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn filter_history_selects_correct_budget() {
|
||||
let x_id = ParamId::new();
|
||||
let dist = Distribution::Float(FloatDistribution {
|
||||
low: 0.0,
|
||||
high: 1.0,
|
||||
log_scale: false,
|
||||
step: None,
|
||||
});
|
||||
|
||||
let history = vec![
|
||||
make_trial_with_intermediates(
|
||||
0,
|
||||
0.5,
|
||||
vec![(x_id, ParamValue::Float(0.3), dist.clone())],
|
||||
vec![(1, 0.9), (3, 0.7), (9, 0.5)],
|
||||
),
|
||||
make_trial_with_intermediates(
|
||||
1,
|
||||
0.4,
|
||||
vec![(x_id, ParamValue::Float(0.6), dist.clone())],
|
||||
vec![(1, 0.8), (3, 0.4)],
|
||||
),
|
||||
make_trial_with_intermediates(
|
||||
2,
|
||||
0.3,
|
||||
vec![(x_id, ParamValue::Float(0.1), dist.clone())],
|
||||
vec![(1, 0.7)],
|
||||
),
|
||||
];
|
||||
|
||||
// Budget 3: trials 0 and 1 have intermediate values at step 3
|
||||
let filtered = BohbSampler::filter_history_for_budget(&history, 3);
|
||||
assert_eq!(filtered.len(), 2);
|
||||
assert!((filtered[0].value - 0.7).abs() < f64::EPSILON);
|
||||
assert!((filtered[1].value - 0.4).abs() < f64::EPSILON);
|
||||
|
||||
// Budget 9: only trial 0
|
||||
let filtered = BohbSampler::filter_history_for_budget(&history, 9);
|
||||
assert_eq!(filtered.len(), 1);
|
||||
assert!((filtered[0].value - 0.5).abs() < f64::EPSILON);
|
||||
|
||||
// Budget 27: nobody
|
||||
let filtered = BohbSampler::filter_history_for_budget(&history, 27);
|
||||
assert!(filtered.is_empty());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn matching_pruner_has_same_params() {
|
||||
let bohb = BohbSampler::builder()
|
||||
.min_resource(2)
|
||||
.max_resource(64)
|
||||
.reduction_factor(4)
|
||||
.build()
|
||||
.unwrap();
|
||||
let pruner = bohb.matching_pruner(Direction::Minimize);
|
||||
|
||||
// We can't directly inspect HyperbandPruner fields, but we can
|
||||
// verify it was created without panicking with the same params.
|
||||
// The pruner's rung steps should match BOHB's budget levels.
|
||||
// Just verify it doesn't panic.
|
||||
drop(pruner);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn fallback_to_random_when_insufficient_data() {
|
||||
let bohb = BohbSampler::builder()
|
||||
.min_points_in_model(10)
|
||||
.seed(42)
|
||||
.build()
|
||||
.unwrap();
|
||||
|
||||
let dist = Distribution::Float(FloatDistribution {
|
||||
low: 0.0,
|
||||
high: 1.0,
|
||||
log_scale: false,
|
||||
step: None,
|
||||
});
|
||||
|
||||
// Only 3 trials with intermediate values (< min_points_in_model=10)
|
||||
let x_id = ParamId::new();
|
||||
let history: Vec<CompletedTrial> = (0..3)
|
||||
.map(|i| {
|
||||
make_trial_with_intermediates(
|
||||
i,
|
||||
i as f64,
|
||||
vec![(x_id, ParamValue::Float(i as f64 / 3.0), dist.clone())],
|
||||
vec![(1, i as f64)],
|
||||
)
|
||||
})
|
||||
.collect();
|
||||
|
||||
// Should not panic, should sample within bounds
|
||||
for trial_id in 0..20 {
|
||||
let val = bohb.sample(&dist, trial_id, &history);
|
||||
if let ParamValue::Float(v) = val {
|
||||
assert!((0.0..=1.0).contains(&v));
|
||||
} else {
|
||||
panic!("Expected Float");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn uses_budget_level_when_enough_data() {
|
||||
let bohb = BohbSampler::builder()
|
||||
.min_points_in_model(5)
|
||||
.seed(42)
|
||||
.build()
|
||||
.unwrap();
|
||||
|
||||
let dist = Distribution::Float(FloatDistribution {
|
||||
low: 0.0,
|
||||
high: 10.0,
|
||||
log_scale: false,
|
||||
step: None,
|
||||
});
|
||||
|
||||
// Create 20 trials with intermediate values at budget 1.
|
||||
// Good trials have x near 2.0, bad trials have x far from 2.0.
|
||||
let x_id = ParamId::new();
|
||||
let history: Vec<CompletedTrial> = (0..20)
|
||||
.map(|i| {
|
||||
let x = i as f64 / 2.0;
|
||||
let iv_at_1 = (x - 2.0).powi(2);
|
||||
make_trial_with_intermediates(
|
||||
i,
|
||||
iv_at_1, // final value same as intermediate for simplicity
|
||||
vec![(x_id, ParamValue::Float(x), dist.clone())],
|
||||
vec![(1, iv_at_1)],
|
||||
)
|
||||
})
|
||||
.collect();
|
||||
|
||||
// Should use TPE on filtered history at budget 1
|
||||
let val = bohb.sample(&dist, 100, &history);
|
||||
if let ParamValue::Float(v) = val {
|
||||
assert!((0.0..=10.0).contains(&v), "Value {v} out of bounds");
|
||||
} else {
|
||||
panic!("Expected Float");
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn prefers_largest_budget_level() {
|
||||
let bohb = BohbSampler::builder()
|
||||
.min_resource(1)
|
||||
.max_resource(9)
|
||||
.reduction_factor(3)
|
||||
.min_points_in_model(3)
|
||||
.seed(42)
|
||||
.build()
|
||||
.unwrap();
|
||||
|
||||
let dist = Distribution::Float(FloatDistribution {
|
||||
low: 0.0,
|
||||
high: 10.0,
|
||||
log_scale: false,
|
||||
step: None,
|
||||
});
|
||||
|
||||
// Budget levels: [1, 3, 9]
|
||||
assert_eq!(bohb.all_budget_levels(), vec![1, 3, 9]);
|
||||
|
||||
// Create 5 trials with intermediates at budget 1 and 3
|
||||
let x_id = ParamId::new();
|
||||
let history: Vec<CompletedTrial> = (0..5)
|
||||
.map(|i| {
|
||||
let x = i as f64;
|
||||
make_trial_with_intermediates(
|
||||
i,
|
||||
x,
|
||||
vec![(x_id, ParamValue::Float(x), dist.clone())],
|
||||
vec![(1, x * 2.0), (3, x)],
|
||||
)
|
||||
})
|
||||
.collect();
|
||||
|
||||
// Budget 3 has 5 observations (>= 3), budget 9 has 0.
|
||||
// BOHB should pick budget 3 (largest with enough data).
|
||||
// The filtered history at budget 3 has values [0, 1, 2, 3, 4].
|
||||
let filtered_3 = BohbSampler::filter_history_for_budget(&history, 3);
|
||||
assert_eq!(filtered_3.len(), 5);
|
||||
let filtered_9 = BohbSampler::filter_history_for_budget(&history, 9);
|
||||
assert_eq!(filtered_9.len(), 0);
|
||||
|
||||
// Should sample successfully
|
||||
let val = bohb.sample(&dist, 100, &history);
|
||||
assert!(matches!(val, ParamValue::Float(_)));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn builder_validates_tpe_params() {
|
||||
// Invalid gamma
|
||||
let result = BohbSampler::builder().gamma(1.5).build();
|
||||
assert!(result.is_err());
|
||||
|
||||
// Invalid bandwidth
|
||||
let result = BohbSampler::builder().kde_bandwidth(-1.0).build();
|
||||
assert!(result.is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
#[should_panic(expected = "min_resource must be > 0")]
|
||||
fn builder_rejects_zero_min_resource() {
|
||||
let _ = BohbSampler::builder().min_resource(0);
|
||||
}
|
||||
|
||||
#[test]
|
||||
#[should_panic(expected = "max_resource must be > 0")]
|
||||
fn builder_rejects_zero_max_resource() {
|
||||
let _ = BohbSampler::builder().max_resource(0);
|
||||
}
|
||||
|
||||
#[test]
|
||||
#[should_panic(expected = "reduction_factor must be >= 2")]
|
||||
fn builder_rejects_small_reduction_factor() {
|
||||
let _ = BohbSampler::builder().reduction_factor(1);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn int_distribution_works() {
|
||||
let bohb = BohbSampler::builder()
|
||||
.min_points_in_model(3)
|
||||
.seed(42)
|
||||
.build()
|
||||
.unwrap();
|
||||
|
||||
let dist = Distribution::Int(IntDistribution {
|
||||
low: 0,
|
||||
high: 100,
|
||||
log_scale: false,
|
||||
step: None,
|
||||
});
|
||||
|
||||
let x_id = ParamId::new();
|
||||
let history: Vec<CompletedTrial> = (0..10)
|
||||
.map(|i| {
|
||||
make_trial_with_intermediates(
|
||||
i,
|
||||
i as f64,
|
||||
vec![(x_id, ParamValue::Int(i.cast_signed() * 10), dist.clone())],
|
||||
vec![(1, i as f64)],
|
||||
)
|
||||
})
|
||||
.collect();
|
||||
|
||||
let val = bohb.sample(&dist, 100, &history);
|
||||
if let ParamValue::Int(v) = val {
|
||||
assert!((0..=100).contains(&v));
|
||||
} else {
|
||||
panic!("Expected Int");
|
||||
}
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,7 +1,12 @@
|
||||
//! Sampler trait and implementations for parameter sampling.
|
||||
|
||||
pub mod bohb;
|
||||
#[cfg(feature = "cma-es")]
|
||||
pub mod cma_es;
|
||||
pub mod grid;
|
||||
pub mod random;
|
||||
#[cfg(feature = "sobol")]
|
||||
pub mod sobol;
|
||||
pub mod tpe;
|
||||
|
||||
use std::collections::HashMap;
|
||||
@@ -9,6 +14,8 @@ use std::collections::HashMap;
|
||||
use crate::distribution::Distribution;
|
||||
use crate::param::ParamValue;
|
||||
use crate::parameter::{ParamId, Parameter};
|
||||
use crate::trial::AttrValue;
|
||||
use crate::types::TrialState;
|
||||
|
||||
/// A completed trial with its parameters, distributions, and objective value.
|
||||
///
|
||||
@@ -16,6 +23,7 @@ use crate::parameter::{ParamId, Parameter};
|
||||
/// parameter values, their distributions, and the objective value returned
|
||||
/// by the objective function.
|
||||
#[derive(Clone, Debug)]
|
||||
#[cfg_attr(feature = "serde", derive(serde::Serialize, serde::Deserialize))]
|
||||
pub struct CompletedTrial<V = f64> {
|
||||
/// The unique identifier for this trial.
|
||||
pub id: u64,
|
||||
@@ -27,6 +35,15 @@ pub struct CompletedTrial<V = f64> {
|
||||
pub param_labels: HashMap<ParamId, String>,
|
||||
/// The objective value returned by the objective function.
|
||||
pub value: V,
|
||||
/// Intermediate objective values reported during the trial.
|
||||
pub intermediate_values: Vec<(u64, f64)>,
|
||||
/// The state of the trial (Complete, Pruned, or Failed).
|
||||
pub state: TrialState,
|
||||
/// User-defined attributes stored during the trial.
|
||||
pub user_attrs: HashMap<String, AttrValue>,
|
||||
/// Constraint values for this trial (<=0.0 means feasible).
|
||||
#[cfg_attr(feature = "serde", serde(default))]
|
||||
pub constraints: Vec<f64>,
|
||||
}
|
||||
|
||||
impl<V> CompletedTrial<V> {
|
||||
@@ -44,6 +61,33 @@ impl<V> CompletedTrial<V> {
|
||||
distributions,
|
||||
param_labels,
|
||||
value,
|
||||
intermediate_values: Vec::new(),
|
||||
state: TrialState::Complete,
|
||||
user_attrs: HashMap::new(),
|
||||
constraints: Vec::new(),
|
||||
}
|
||||
}
|
||||
|
||||
/// Creates a new completed trial with intermediate values and user attributes.
|
||||
pub fn with_intermediate_values(
|
||||
id: u64,
|
||||
params: HashMap<ParamId, ParamValue>,
|
||||
distributions: HashMap<ParamId, Distribution>,
|
||||
param_labels: HashMap<ParamId, String>,
|
||||
value: V,
|
||||
intermediate_values: Vec<(u64, f64)>,
|
||||
user_attrs: HashMap<String, AttrValue>,
|
||||
) -> Self {
|
||||
Self {
|
||||
id,
|
||||
params,
|
||||
distributions,
|
||||
param_labels,
|
||||
value,
|
||||
intermediate_values,
|
||||
state: TrialState::Complete,
|
||||
user_attrs,
|
||||
constraints: Vec::new(),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -87,6 +131,26 @@ impl<V> CompletedTrial<V> {
|
||||
.expect("parameter type mismatch: stored value incompatible with parameter")
|
||||
})
|
||||
}
|
||||
|
||||
/// Returns `true` if all constraints are satisfied (values <= 0.0).
|
||||
///
|
||||
/// A trial with no constraints is considered feasible.
|
||||
#[must_use]
|
||||
pub fn is_feasible(&self) -> bool {
|
||||
self.constraints.iter().all(|&c| c <= 0.0)
|
||||
}
|
||||
|
||||
/// Gets a user attribute by key.
|
||||
#[must_use]
|
||||
pub fn user_attr(&self, key: &str) -> Option<&AttrValue> {
|
||||
self.user_attrs.get(key)
|
||||
}
|
||||
|
||||
/// Returns all user attributes.
|
||||
#[must_use]
|
||||
pub fn user_attrs(&self) -> &HashMap<String, AttrValue> {
|
||||
&self.user_attrs
|
||||
}
|
||||
}
|
||||
|
||||
/// A pending (running) trial with its parameters and distributions, but no objective value yet.
|
||||
|
||||
@@ -0,0 +1,420 @@
|
||||
//! Quasi-random sampler using Sobol low-discrepancy sequences.
|
||||
|
||||
use parking_lot::Mutex;
|
||||
use sobol_burley::sample;
|
||||
|
||||
use crate::distribution::Distribution;
|
||||
use crate::param::ParamValue;
|
||||
use crate::sampler::{CompletedTrial, Sampler};
|
||||
|
||||
/// Internal state for tracking the dimension counter within a trial.
|
||||
struct SobolState {
|
||||
/// The `trial_id` of the current trial (used to reset dimension counter).
|
||||
current_trial: u64,
|
||||
/// Next Sobol dimension to use for the current trial.
|
||||
next_dimension: u32,
|
||||
}
|
||||
|
||||
/// Quasi-random sampler using Sobol low-discrepancy sequences.
|
||||
///
|
||||
/// Provides better uniform coverage of the parameter space than
|
||||
/// [`RandomSampler`](super::random::RandomSampler). Useful as a baseline or
|
||||
/// for the startup phase of model-based samplers.
|
||||
///
|
||||
/// Unlike random sampling, Sobol sequences are deterministic and fill the
|
||||
/// space more evenly, reducing the number of trials needed to adequately
|
||||
/// cover the search space.
|
||||
///
|
||||
/// Each trial uses a different Sobol sequence index, and each parameter
|
||||
/// within a trial maps to a different Sobol dimension. Parameters must be
|
||||
/// suggested in the same order across trials for consistent dimension
|
||||
/// assignment.
|
||||
///
|
||||
/// Sobol sequences are most effective in moderate dimensions (up to ~20).
|
||||
/// For very high dimensions, the uniformity advantage diminishes.
|
||||
///
|
||||
/// Requires the `sobol` feature flag.
|
||||
///
|
||||
/// # Examples
|
||||
///
|
||||
/// ```
|
||||
/// use optimizer::sampler::sobol::SobolSampler;
|
||||
/// use optimizer::{Direction, Study};
|
||||
///
|
||||
/// let study: Study<f64> = Study::with_sampler(Direction::Minimize, SobolSampler::new());
|
||||
/// ```
|
||||
pub struct SobolSampler {
|
||||
seed: u32,
|
||||
state: Mutex<SobolState>,
|
||||
}
|
||||
|
||||
impl SobolSampler {
|
||||
/// Creates a new Sobol sampler with a default seed of 0.
|
||||
#[must_use]
|
||||
pub fn new() -> Self {
|
||||
Self::with_seed(0)
|
||||
}
|
||||
|
||||
/// Creates a new Sobol sampler with the given seed.
|
||||
///
|
||||
/// Different seeds produce statistically independent Sobol sequences.
|
||||
/// Using the same seed will produce the same sequence of sampled values.
|
||||
#[must_use]
|
||||
#[allow(clippy::cast_possible_truncation)]
|
||||
pub fn with_seed(seed: u64) -> Self {
|
||||
Self {
|
||||
seed: seed as u32,
|
||||
state: Mutex::new(SobolState {
|
||||
current_trial: u64::MAX,
|
||||
next_dimension: 0,
|
||||
}),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
impl Default for SobolSampler {
|
||||
fn default() -> Self {
|
||||
Self::new()
|
||||
}
|
||||
}
|
||||
|
||||
impl Sampler for SobolSampler {
|
||||
#[allow(clippy::cast_possible_truncation, clippy::cast_precision_loss)]
|
||||
fn sample(
|
||||
&self,
|
||||
distribution: &Distribution,
|
||||
trial_id: u64,
|
||||
_history: &[CompletedTrial],
|
||||
) -> ParamValue {
|
||||
let mut state = self.state.lock();
|
||||
|
||||
// Reset dimension counter when a new trial starts.
|
||||
if state.current_trial != trial_id {
|
||||
state.current_trial = trial_id;
|
||||
state.next_dimension = 0;
|
||||
}
|
||||
|
||||
let dimension = state.next_dimension;
|
||||
state.next_dimension = dimension + 1;
|
||||
|
||||
// Use trial_id as the Sobol sequence index.
|
||||
let index = trial_id as u32;
|
||||
|
||||
// Generate a quasi-random point in [0, 1).
|
||||
let point = f64::from(sample(index, dimension, self.seed));
|
||||
|
||||
map_point_to_distribution(point, distribution)
|
||||
}
|
||||
}
|
||||
|
||||
/// Maps a uniform [0, 1) point to a value within the given distribution.
|
||||
#[allow(
|
||||
clippy::cast_possible_truncation,
|
||||
clippy::cast_precision_loss,
|
||||
clippy::cast_sign_loss
|
||||
)]
|
||||
fn map_point_to_distribution(point: f64, distribution: &Distribution) -> ParamValue {
|
||||
match distribution {
|
||||
Distribution::Float(d) => {
|
||||
let value = if d.log_scale {
|
||||
let log_low = d.low.ln();
|
||||
let log_high = d.high.ln();
|
||||
(log_low + point * (log_high - log_low)).exp()
|
||||
} else if let Some(step) = d.step {
|
||||
let n_steps = ((d.high - d.low) / step).floor() as i64;
|
||||
let k = (point * (n_steps + 1) as f64).floor() as i64;
|
||||
let k = k.min(n_steps);
|
||||
d.low + (k as f64) * step
|
||||
} else {
|
||||
d.low + point * (d.high - d.low)
|
||||
};
|
||||
ParamValue::Float(value)
|
||||
}
|
||||
Distribution::Int(d) => {
|
||||
let value = if d.log_scale {
|
||||
let log_low = (d.low as f64).ln();
|
||||
let log_high = (d.high as f64).ln();
|
||||
let raw = (log_low + point * (log_high - log_low)).exp().round() as i64;
|
||||
raw.clamp(d.low, d.high)
|
||||
} else if let Some(step) = d.step {
|
||||
let n_steps = (d.high - d.low) / step;
|
||||
let k = (point * (n_steps + 1) as f64).floor() as i64;
|
||||
let k = k.min(n_steps);
|
||||
d.low + k * step
|
||||
} else {
|
||||
let range = d.high - d.low + 1;
|
||||
let k = (point * range as f64).floor() as i64;
|
||||
(d.low + k).min(d.high)
|
||||
};
|
||||
ParamValue::Int(value)
|
||||
}
|
||||
Distribution::Categorical(d) => {
|
||||
let index = (point * d.n_choices as f64).floor() as usize;
|
||||
let index = index.min(d.n_choices - 1);
|
||||
ParamValue::Categorical(index)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
#[allow(
|
||||
clippy::cast_possible_truncation,
|
||||
clippy::cast_precision_loss,
|
||||
clippy::cast_sign_loss
|
||||
)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use crate::distribution::{CategoricalDistribution, FloatDistribution, IntDistribution};
|
||||
|
||||
#[test]
|
||||
fn float_within_bounds() {
|
||||
let sampler = SobolSampler::with_seed(42);
|
||||
let dist = Distribution::Float(FloatDistribution {
|
||||
low: -5.0,
|
||||
high: 5.0,
|
||||
log_scale: false,
|
||||
step: None,
|
||||
});
|
||||
|
||||
for i in 0..100 {
|
||||
let value = sampler.sample(&dist, i, &[]);
|
||||
if let ParamValue::Float(v) = value {
|
||||
assert!(
|
||||
(-5.0..=5.0).contains(&v),
|
||||
"value {v} out of bounds at trial {i}"
|
||||
);
|
||||
} else {
|
||||
panic!("Expected Float value");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn float_log_scale_within_bounds() {
|
||||
let sampler = SobolSampler::with_seed(42);
|
||||
let dist = Distribution::Float(FloatDistribution {
|
||||
low: 1e-5,
|
||||
high: 1.0,
|
||||
log_scale: true,
|
||||
step: None,
|
||||
});
|
||||
|
||||
for i in 0..100 {
|
||||
let value = sampler.sample(&dist, i, &[]);
|
||||
if let ParamValue::Float(v) = value {
|
||||
assert!(
|
||||
(1e-5..=1.0).contains(&v),
|
||||
"value {v} out of bounds at trial {i}"
|
||||
);
|
||||
} else {
|
||||
panic!("Expected Float value");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn float_step_respects_grid() {
|
||||
let sampler = SobolSampler::with_seed(42);
|
||||
let dist = Distribution::Float(FloatDistribution {
|
||||
low: 0.0,
|
||||
high: 1.0,
|
||||
log_scale: false,
|
||||
step: Some(0.25),
|
||||
});
|
||||
|
||||
for i in 0..100 {
|
||||
let value = sampler.sample(&dist, i, &[]);
|
||||
if let ParamValue::Float(v) = value {
|
||||
assert!((0.0..=1.0).contains(&v), "value {v} out of bounds");
|
||||
let k = (v / 0.25).round() as i64;
|
||||
let expected = k as f64 * 0.25;
|
||||
assert!((v - expected).abs() < 1e-10, "value {v} not on step grid");
|
||||
} else {
|
||||
panic!("Expected Float value");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn int_within_bounds() {
|
||||
let sampler = SobolSampler::with_seed(42);
|
||||
let dist = Distribution::Int(IntDistribution {
|
||||
low: 0,
|
||||
high: 10,
|
||||
log_scale: false,
|
||||
step: None,
|
||||
});
|
||||
|
||||
for i in 0..100 {
|
||||
let value = sampler.sample(&dist, i, &[]);
|
||||
if let ParamValue::Int(v) = value {
|
||||
assert!(
|
||||
(0..=10).contains(&v),
|
||||
"value {v} out of bounds at trial {i}"
|
||||
);
|
||||
} else {
|
||||
panic!("Expected Int value");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn int_log_scale_within_bounds() {
|
||||
let sampler = SobolSampler::with_seed(42);
|
||||
let dist = Distribution::Int(IntDistribution {
|
||||
low: 1,
|
||||
high: 1000,
|
||||
log_scale: true,
|
||||
step: None,
|
||||
});
|
||||
|
||||
for i in 0..100 {
|
||||
let value = sampler.sample(&dist, i, &[]);
|
||||
if let ParamValue::Int(v) = value {
|
||||
assert!(
|
||||
(1..=1000).contains(&v),
|
||||
"value {v} out of bounds at trial {i}"
|
||||
);
|
||||
} else {
|
||||
panic!("Expected Int value");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn int_step_respects_grid() {
|
||||
let sampler = SobolSampler::with_seed(42);
|
||||
let dist = Distribution::Int(IntDistribution {
|
||||
low: 0,
|
||||
high: 10,
|
||||
log_scale: false,
|
||||
step: Some(2),
|
||||
});
|
||||
|
||||
for i in 0..100 {
|
||||
let value = sampler.sample(&dist, i, &[]);
|
||||
if let ParamValue::Int(v) = value {
|
||||
assert!((0..=10).contains(&v), "value {v} out of bounds");
|
||||
assert!(v % 2 == 0, "value {v} not on step grid");
|
||||
} else {
|
||||
panic!("Expected Int value");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn categorical_within_bounds() {
|
||||
let sampler = SobolSampler::with_seed(42);
|
||||
let dist = Distribution::Categorical(CategoricalDistribution { n_choices: 5 });
|
||||
|
||||
for i in 0..100 {
|
||||
let value = sampler.sample(&dist, i, &[]);
|
||||
if let ParamValue::Categorical(idx) = value {
|
||||
assert!(idx < 5, "index {idx} out of bounds at trial {i}");
|
||||
} else {
|
||||
panic!("Expected Categorical value");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn deterministic_with_same_seed() {
|
||||
let dist = Distribution::Float(FloatDistribution {
|
||||
low: 0.0,
|
||||
high: 1.0,
|
||||
log_scale: false,
|
||||
step: None,
|
||||
});
|
||||
|
||||
let sampler1 = SobolSampler::with_seed(42);
|
||||
let sampler2 = SobolSampler::with_seed(42);
|
||||
|
||||
for i in 0..20 {
|
||||
let v1 = sampler1.sample(&dist, i, &[]);
|
||||
let v2 = sampler2.sample(&dist, i, &[]);
|
||||
assert_eq!(v1, v2, "mismatch at trial {i}");
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn different_seeds_produce_different_sequences() {
|
||||
let dist = Distribution::Float(FloatDistribution {
|
||||
low: 0.0,
|
||||
high: 1.0,
|
||||
log_scale: false,
|
||||
step: None,
|
||||
});
|
||||
|
||||
let sampler1 = SobolSampler::with_seed(0);
|
||||
let sampler2 = SobolSampler::with_seed(12345);
|
||||
|
||||
let mut any_different = false;
|
||||
for i in 0..20 {
|
||||
let v1 = sampler1.sample(&dist, i, &[]);
|
||||
let v2 = sampler2.sample(&dist, i, &[]);
|
||||
if v1 != v2 {
|
||||
any_different = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
assert!(
|
||||
any_different,
|
||||
"different seeds should produce different sequences"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn better_coverage_than_random() {
|
||||
// Sobol sequence should cover [0,1] more uniformly than random.
|
||||
// We measure this by checking that the Sobol samples fill all
|
||||
// 10 equal-width bins with only 20 samples.
|
||||
let sampler = SobolSampler::with_seed(0);
|
||||
let dist = Distribution::Float(FloatDistribution {
|
||||
low: 0.0,
|
||||
high: 1.0,
|
||||
log_scale: false,
|
||||
step: None,
|
||||
});
|
||||
|
||||
let n_bins = 10;
|
||||
let n_samples = 20;
|
||||
let mut bins = vec![0u32; n_bins];
|
||||
|
||||
for i in 0..n_samples {
|
||||
let value = sampler.sample(&dist, i, &[]);
|
||||
if let ParamValue::Float(v) = value {
|
||||
let bin = ((v * n_bins as f64).floor() as usize).min(n_bins - 1);
|
||||
bins[bin] += 1;
|
||||
}
|
||||
}
|
||||
|
||||
let filled_bins = bins.iter().filter(|&&c| c > 0).count();
|
||||
assert!(
|
||||
filled_bins >= 8,
|
||||
"Expected at least 8/10 bins filled, got {filled_bins}: {bins:?}"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn multi_parameter_uses_different_dimensions() {
|
||||
// When sampling multiple parameters per trial, each parameter
|
||||
// should get a different Sobol dimension, producing different values.
|
||||
let sampler = SobolSampler::with_seed(0);
|
||||
let dist = Distribution::Float(FloatDistribution {
|
||||
low: 0.0,
|
||||
high: 1.0,
|
||||
log_scale: false,
|
||||
step: None,
|
||||
});
|
||||
|
||||
// Sample two parameters for trial 0.
|
||||
let v1 = sampler.sample(&dist, 0, &[]);
|
||||
let v2 = sampler.sample(&dist, 0, &[]);
|
||||
|
||||
// They should differ (different Sobol dimensions for the same index).
|
||||
assert_ne!(
|
||||
v1, v2,
|
||||
"multi-parameter samples should use different dimensions"
|
||||
);
|
||||
}
|
||||
}
|
||||
+1296
-41
File diff suppressed because it is too large
Load Diff
+172
-2
@@ -9,9 +9,54 @@ use crate::distribution::Distribution;
|
||||
use crate::error::{Error, Result};
|
||||
use crate::param::ParamValue;
|
||||
use crate::parameter::{ParamId, Parameter};
|
||||
use crate::pruner::Pruner;
|
||||
use crate::sampler::{CompletedTrial, Sampler};
|
||||
use crate::types::TrialState;
|
||||
|
||||
/// A user attribute value that can be stored on a trial.
|
||||
#[derive(Clone, Debug, PartialEq)]
|
||||
#[cfg_attr(feature = "serde", derive(serde::Serialize, serde::Deserialize))]
|
||||
pub enum AttrValue {
|
||||
/// A floating-point attribute.
|
||||
Float(f64),
|
||||
/// An integer attribute.
|
||||
Int(i64),
|
||||
/// A string attribute.
|
||||
String(String),
|
||||
/// A boolean attribute.
|
||||
Bool(bool),
|
||||
}
|
||||
|
||||
impl From<f64> for AttrValue {
|
||||
fn from(v: f64) -> Self {
|
||||
Self::Float(v)
|
||||
}
|
||||
}
|
||||
|
||||
impl From<i64> for AttrValue {
|
||||
fn from(v: i64) -> Self {
|
||||
Self::Int(v)
|
||||
}
|
||||
}
|
||||
|
||||
impl From<String> for AttrValue {
|
||||
fn from(v: String) -> Self {
|
||||
Self::String(v)
|
||||
}
|
||||
}
|
||||
|
||||
impl From<&str> for AttrValue {
|
||||
fn from(v: &str) -> Self {
|
||||
Self::String(v.to_owned())
|
||||
}
|
||||
}
|
||||
|
||||
impl From<bool> for AttrValue {
|
||||
fn from(v: bool) -> Self {
|
||||
Self::Bool(v)
|
||||
}
|
||||
}
|
||||
|
||||
/// A trial represents a single evaluation of the objective function.
|
||||
///
|
||||
/// Each trial has a unique ID and stores the sampled parameters along with
|
||||
@@ -36,6 +81,16 @@ pub struct Trial {
|
||||
sampler: Option<Arc<dyn Sampler>>,
|
||||
/// Access to the history of completed trials (shared with Study).
|
||||
history: Option<Arc<RwLock<Vec<CompletedTrial<f64>>>>>,
|
||||
/// Intermediate objective values reported at each step.
|
||||
intermediate_values: Vec<(u64, f64)>,
|
||||
/// The pruner used to decide whether to stop this trial early.
|
||||
pruner: Option<Arc<dyn Pruner>>,
|
||||
/// User-defined attributes for logging, debugging, and analysis.
|
||||
user_attrs: HashMap<String, AttrValue>,
|
||||
/// Pre-filled parameter values from enqueue (used instead of sampling).
|
||||
fixed_params: HashMap<ParamId, ParamValue>,
|
||||
/// Constraint values for this trial (<=0.0 means feasible).
|
||||
constraint_values: Vec<f64>,
|
||||
}
|
||||
|
||||
impl core::fmt::Debug for Trial {
|
||||
@@ -48,6 +103,11 @@ impl core::fmt::Debug for Trial {
|
||||
.field("param_labels", &self.param_labels)
|
||||
.field("has_sampler", &self.sampler.is_some())
|
||||
.field("has_history", &self.history.is_some())
|
||||
.field("intermediate_values", &self.intermediate_values)
|
||||
.field("has_pruner", &self.pruner.is_some())
|
||||
.field("user_attrs", &self.user_attrs)
|
||||
.field("fixed_params", &self.fixed_params)
|
||||
.field("constraint_values", &self.constraint_values)
|
||||
.finish()
|
||||
}
|
||||
}
|
||||
@@ -83,6 +143,11 @@ impl Trial {
|
||||
param_labels: HashMap::new(),
|
||||
sampler: None,
|
||||
history: None,
|
||||
intermediate_values: Vec::new(),
|
||||
pruner: None,
|
||||
user_attrs: HashMap::new(),
|
||||
fixed_params: HashMap::new(),
|
||||
constraint_values: Vec::new(),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -100,6 +165,7 @@ impl Trial {
|
||||
id: u64,
|
||||
sampler: Arc<dyn Sampler>,
|
||||
history: Arc<RwLock<Vec<CompletedTrial<f64>>>>,
|
||||
pruner: Arc<dyn Pruner>,
|
||||
) -> Self {
|
||||
Self {
|
||||
id,
|
||||
@@ -109,9 +175,22 @@ impl Trial {
|
||||
param_labels: HashMap::new(),
|
||||
sampler: Some(sampler),
|
||||
history: Some(history),
|
||||
intermediate_values: Vec::new(),
|
||||
pruner: Some(pruner),
|
||||
user_attrs: HashMap::new(),
|
||||
fixed_params: HashMap::new(),
|
||||
constraint_values: Vec::new(),
|
||||
}
|
||||
}
|
||||
|
||||
/// Sets pre-filled parameters on this trial.
|
||||
///
|
||||
/// When `suggest_param` is called for a parameter that has a fixed value,
|
||||
/// the fixed value is used instead of sampling.
|
||||
pub(crate) fn set_fixed_params(&mut self, params: HashMap<ParamId, ParamValue>) {
|
||||
self.fixed_params = params;
|
||||
}
|
||||
|
||||
/// Samples a value from the given distribution using the sampler.
|
||||
///
|
||||
/// If the trial has a sampler, it delegates to the sampler's sample method
|
||||
@@ -159,6 +238,79 @@ impl Trial {
|
||||
&self.param_labels
|
||||
}
|
||||
|
||||
/// Reports an intermediate objective value at a given step.
|
||||
///
|
||||
/// Steps should be monotonically increasing (e.g., epoch number).
|
||||
/// Duplicate steps overwrite the previous value.
|
||||
pub fn report(&mut self, step: u64, value: f64) {
|
||||
if let Some(entry) = self
|
||||
.intermediate_values
|
||||
.iter_mut()
|
||||
.find(|(s, _)| *s == step)
|
||||
{
|
||||
entry.1 = value;
|
||||
} else {
|
||||
self.intermediate_values.push((step, value));
|
||||
}
|
||||
}
|
||||
|
||||
/// Ask whether this trial should be pruned at the current step.
|
||||
///
|
||||
/// Returns `true` if the pruner recommends stopping this trial.
|
||||
/// The caller should return `Err(TrialPruned)` from the objective.
|
||||
#[must_use]
|
||||
pub fn should_prune(&self) -> bool {
|
||||
let (Some(pruner), Some(history)) = (&self.pruner, &self.history) else {
|
||||
return false;
|
||||
};
|
||||
let Some(&(step, _)) = self.intermediate_values.last() else {
|
||||
return false;
|
||||
};
|
||||
let history_guard = history.read();
|
||||
let prune = pruner.should_prune(self.id, step, &self.intermediate_values, &history_guard);
|
||||
if prune {
|
||||
trace_info!(trial_id = self.id, step, "pruner recommends stopping");
|
||||
}
|
||||
prune
|
||||
}
|
||||
|
||||
/// Returns all intermediate values reported so far.
|
||||
#[must_use]
|
||||
pub fn intermediate_values(&self) -> &[(u64, f64)] {
|
||||
&self.intermediate_values
|
||||
}
|
||||
|
||||
/// Sets a user attribute on this trial.
|
||||
pub fn set_user_attr(&mut self, key: impl Into<String>, value: impl Into<AttrValue>) {
|
||||
self.user_attrs.insert(key.into(), value.into());
|
||||
}
|
||||
|
||||
/// Gets a user attribute by key.
|
||||
#[must_use]
|
||||
pub fn user_attr(&self, key: &str) -> Option<&AttrValue> {
|
||||
self.user_attrs.get(key)
|
||||
}
|
||||
|
||||
/// Returns all user attributes.
|
||||
#[must_use]
|
||||
pub fn user_attrs(&self) -> &HashMap<String, AttrValue> {
|
||||
&self.user_attrs
|
||||
}
|
||||
|
||||
/// Sets constraint values for this trial.
|
||||
///
|
||||
/// Each value represents a constraint; a value <= 0.0 means the constraint
|
||||
/// is satisfied (feasible). A value > 0.0 means the constraint is violated.
|
||||
pub fn set_constraints(&mut self, values: Vec<f64>) {
|
||||
self.constraint_values = values;
|
||||
}
|
||||
|
||||
/// Returns the constraint values for this trial.
|
||||
#[must_use]
|
||||
pub fn constraint_values(&self) -> &[f64] {
|
||||
&self.constraint_values
|
||||
}
|
||||
|
||||
/// Sets the trial state to Complete.
|
||||
pub(crate) fn set_complete(&mut self) {
|
||||
self.state = TrialState::Complete;
|
||||
@@ -169,6 +321,11 @@ impl Trial {
|
||||
self.state = TrialState::Failed;
|
||||
}
|
||||
|
||||
/// Sets the trial state to Pruned.
|
||||
pub(crate) fn set_pruned(&mut self) {
|
||||
self.state = TrialState::Pruned;
|
||||
}
|
||||
|
||||
/// Suggests a parameter value using a [`Parameter`] definition.
|
||||
///
|
||||
/// This is the primary entry point for sampling parameters. It handles
|
||||
@@ -223,10 +380,23 @@ impl Trial {
|
||||
});
|
||||
}
|
||||
|
||||
// Sample using the sampler
|
||||
let value = self.sample_value(&distribution);
|
||||
// Check for a pre-filled (enqueued) value for this parameter
|
||||
let value = if let Some(fixed_value) = self.fixed_params.remove(¶m_id) {
|
||||
fixed_value
|
||||
} else {
|
||||
// Sample using the sampler
|
||||
self.sample_value(&distribution)
|
||||
};
|
||||
|
||||
let result = param.cast_param_value(&value)?;
|
||||
|
||||
trace_debug!(
|
||||
trial_id = self.id,
|
||||
param = %param.label(),
|
||||
value = %value,
|
||||
"parameter sampled"
|
||||
);
|
||||
|
||||
// Store distribution, value, and label
|
||||
self.distributions.insert(param_id, distribution);
|
||||
self.params.insert(param_id, value);
|
||||
|
||||
@@ -2,6 +2,7 @@
|
||||
|
||||
/// The direction of optimization.
|
||||
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
|
||||
#[cfg_attr(feature = "serde", derive(serde::Serialize, serde::Deserialize))]
|
||||
pub enum Direction {
|
||||
/// Minimize the objective value.
|
||||
Minimize,
|
||||
@@ -11,6 +12,7 @@ pub enum Direction {
|
||||
|
||||
/// The state of a trial in its lifecycle.
|
||||
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
|
||||
#[cfg_attr(feature = "serde", derive(serde::Serialize, serde::Deserialize))]
|
||||
pub enum TrialState {
|
||||
/// The trial is currently running.
|
||||
Running,
|
||||
@@ -18,4 +20,6 @@ pub enum TrialState {
|
||||
Complete,
|
||||
/// The trial failed with an error.
|
||||
Failed,
|
||||
/// The trial was pruned (stopped early).
|
||||
Pruned,
|
||||
}
|
||||
|
||||
@@ -0,0 +1,133 @@
|
||||
//! Integration tests for the BOHB sampler.
|
||||
|
||||
#![allow(
|
||||
clippy::cast_sign_loss,
|
||||
clippy::cast_precision_loss,
|
||||
clippy::cast_possible_truncation
|
||||
)]
|
||||
|
||||
use optimizer::parameter::{FloatParam, Parameter};
|
||||
use optimizer::sampler::bohb::BohbSampler;
|
||||
use optimizer::{Direction, Error, Study, TrialPruned};
|
||||
|
||||
#[test]
|
||||
fn bohb_converges_on_quadratic() {
|
||||
let bohb = BohbSampler::builder()
|
||||
.min_resource(1)
|
||||
.max_resource(9)
|
||||
.reduction_factor(3)
|
||||
.min_points_in_model(5)
|
||||
.seed(42)
|
||||
.build()
|
||||
.unwrap();
|
||||
|
||||
let pruner = bohb.matching_pruner(Direction::Minimize);
|
||||
let study: Study<f64> = Study::with_sampler_and_pruner(Direction::Minimize, bohb, pruner);
|
||||
|
||||
let x_param = FloatParam::new(-10.0, 10.0);
|
||||
|
||||
study
|
||||
.optimize(60, |trial| {
|
||||
let x = x_param.suggest(trial)?;
|
||||
|
||||
// Report intermediate values at budget steps 1, 3, 9
|
||||
let obj = (x - 3.0).powi(2);
|
||||
// Simulate budget-based evaluation with noise decreasing at higher budgets
|
||||
trial.report(1, obj + 5.0);
|
||||
trial.report(3, obj + 1.0);
|
||||
trial.report(9, obj);
|
||||
|
||||
Ok::<_, Error>(obj)
|
||||
})
|
||||
.expect("optimization should succeed");
|
||||
|
||||
let best = study.best_trial().expect("should have trials");
|
||||
assert!(
|
||||
best.value < 10.0,
|
||||
"BOHB should find a reasonable solution, got {}",
|
||||
best.value
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn bohb_with_pruning() {
|
||||
let bohb = BohbSampler::builder()
|
||||
.min_resource(1)
|
||||
.max_resource(27)
|
||||
.reduction_factor(3)
|
||||
.min_points_in_model(3)
|
||||
.seed(123)
|
||||
.build()
|
||||
.unwrap();
|
||||
|
||||
let pruner = bohb.matching_pruner(Direction::Minimize);
|
||||
let study: Study<f64> = Study::with_sampler_and_pruner(Direction::Minimize, bohb, pruner);
|
||||
|
||||
let x_param = FloatParam::new(-5.0, 5.0);
|
||||
|
||||
study
|
||||
.optimize(40, |trial| {
|
||||
let x = x_param.suggest(trial)?;
|
||||
let obj = x * x;
|
||||
|
||||
// Report at each rung step and check for pruning
|
||||
for &step in &[1u64, 3, 9, 27] {
|
||||
let noisy_obj = obj + 10.0 / step as f64;
|
||||
trial.report(step, noisy_obj);
|
||||
|
||||
if trial.should_prune() {
|
||||
return Err(TrialPruned.into());
|
||||
}
|
||||
}
|
||||
|
||||
Ok::<_, Error>(obj)
|
||||
})
|
||||
.expect("optimization should succeed");
|
||||
|
||||
// Verify we have completed trials
|
||||
let best = study.best_trial().expect("should have at least one trial");
|
||||
assert!(
|
||||
best.value < 25.0,
|
||||
"best value {} should be reasonable",
|
||||
best.value
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn bohb_uses_budget_conditioned_history() {
|
||||
// Verify that BOHB conditions on budget level by testing that samples
|
||||
// are influenced by intermediate values, not just final values.
|
||||
let bohb = BohbSampler::builder()
|
||||
.min_resource(1)
|
||||
.max_resource(9)
|
||||
.reduction_factor(3)
|
||||
.min_points_in_model(3)
|
||||
.seed(42)
|
||||
.build()
|
||||
.unwrap();
|
||||
|
||||
let pruner = bohb.matching_pruner(Direction::Minimize);
|
||||
let study: Study<f64> = Study::with_sampler_and_pruner(Direction::Minimize, bohb, pruner);
|
||||
|
||||
let x_param = FloatParam::new(0.0, 10.0);
|
||||
|
||||
study
|
||||
.optimize(30, |trial| {
|
||||
let x = x_param.suggest(trial)?;
|
||||
// Intermediate values that guide optimization toward x=2
|
||||
trial.report(1, (x - 2.0).powi(2) + 1.0);
|
||||
trial.report(3, (x - 2.0).powi(2) + 0.5);
|
||||
trial.report(9, (x - 2.0).powi(2));
|
||||
|
||||
Ok::<_, Error>((x - 2.0).powi(2))
|
||||
})
|
||||
.expect("optimization should succeed");
|
||||
|
||||
let best = study.best_trial().unwrap();
|
||||
let best_x: f64 = best.get(&x_param).unwrap();
|
||||
// Should find x reasonably close to 2.0
|
||||
assert!(
|
||||
(best_x - 2.0).abs() < 5.0,
|
||||
"BOHB should explore near x=2, got x={best_x}"
|
||||
);
|
||||
}
|
||||
@@ -0,0 +1,259 @@
|
||||
#![cfg(feature = "cma-es")]
|
||||
|
||||
use optimizer::prelude::*;
|
||||
use optimizer::sampler::cma_es::CmaEsSampler;
|
||||
|
||||
#[test]
|
||||
fn sphere_function() {
|
||||
let sampler = CmaEsSampler::with_seed(42);
|
||||
let study: Study<f64> = Study::with_sampler(Direction::Minimize, sampler);
|
||||
|
||||
let x = FloatParam::new(-5.0, 5.0).name("x");
|
||||
let y = FloatParam::new(-5.0, 5.0).name("y");
|
||||
|
||||
study
|
||||
.optimize(200, |trial| {
|
||||
let xv = x.suggest(trial)?;
|
||||
let yv = y.suggest(trial)?;
|
||||
Ok::<_, Error>(xv * xv + yv * yv)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let best = study.best_trial().unwrap();
|
||||
assert!(
|
||||
best.value < 1.0,
|
||||
"sphere best value should be < 1.0, got {}",
|
||||
best.value
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rosenbrock_function() {
|
||||
let sampler = CmaEsSampler::builder().population_size(20).seed(42).build();
|
||||
let study: Study<f64> = Study::with_sampler(Direction::Minimize, sampler);
|
||||
|
||||
let x = FloatParam::new(-5.0, 5.0).name("x");
|
||||
let y = FloatParam::new(-5.0, 5.0).name("y");
|
||||
|
||||
study
|
||||
.optimize(300, |trial| {
|
||||
let xv = x.suggest(trial)?;
|
||||
let yv = y.suggest(trial)?;
|
||||
let val = (1.0 - xv).powi(2) + 100.0 * (yv - xv * xv).powi(2);
|
||||
Ok::<_, Error>(val)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let best = study.best_trial().unwrap();
|
||||
// Rosenbrock minimum is 0 at (1, 1); we just check reasonable convergence
|
||||
assert!(
|
||||
best.value < 50.0,
|
||||
"rosenbrock best value should be < 50.0, got {}",
|
||||
best.value
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn bounds_respected() {
|
||||
let sampler = CmaEsSampler::with_seed(123);
|
||||
let study: Study<f64> = Study::with_sampler(Direction::Minimize, sampler);
|
||||
|
||||
let x = FloatParam::new(-2.0, 3.0).name("x");
|
||||
let y = FloatParam::new(0.0, 10.0).name("y");
|
||||
|
||||
study
|
||||
.optimize(100, |trial| {
|
||||
let xv = x.suggest(trial)?;
|
||||
let yv = y.suggest(trial)?;
|
||||
Ok::<_, Error>(xv + yv)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
for trial in study.trials() {
|
||||
let xv: f64 = trial.get(&x).unwrap();
|
||||
let yv: f64 = trial.get(&y).unwrap();
|
||||
assert!((-2.0..=3.0).contains(&xv), "x = {xv} out of bounds [-2, 3]");
|
||||
assert!((0.0..=10.0).contains(&yv), "y = {yv} out of bounds [0, 10]");
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn mixed_params_float_and_categorical() {
|
||||
let sampler = CmaEsSampler::with_seed(42);
|
||||
let study: Study<f64> = Study::with_sampler(Direction::Minimize, sampler);
|
||||
|
||||
let x = FloatParam::new(-5.0, 5.0).name("x");
|
||||
let cat = CategoricalParam::new(vec!["a", "b", "c"]).name("cat");
|
||||
|
||||
study
|
||||
.optimize(50, |trial| {
|
||||
let xv = x.suggest(trial)?;
|
||||
let cv = cat.suggest(trial)?;
|
||||
let penalty = match cv {
|
||||
"a" => 0.0,
|
||||
"b" => 1.0,
|
||||
_ => 2.0,
|
||||
};
|
||||
Ok::<_, Error>(xv * xv + penalty)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let best = study.best_trial().unwrap();
|
||||
// Should find a reasonable value
|
||||
assert!(
|
||||
best.value < 10.0,
|
||||
"best value should be < 10.0, got {}",
|
||||
best.value
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn seeded_reproducibility() {
|
||||
let x = FloatParam::new(-5.0, 5.0).name("x");
|
||||
let y = FloatParam::new(-5.0, 5.0).name("y");
|
||||
|
||||
let run = |seed: u64| {
|
||||
let sampler = CmaEsSampler::with_seed(seed);
|
||||
let study: Study<f64> = Study::with_sampler(Direction::Minimize, sampler);
|
||||
study
|
||||
.optimize(50, |trial| {
|
||||
let xv = x.suggest(trial)?;
|
||||
let yv = y.suggest(trial)?;
|
||||
Ok::<_, Error>(xv * xv + yv * yv)
|
||||
})
|
||||
.unwrap();
|
||||
study.trials().iter().map(|t| t.value).collect::<Vec<_>>()
|
||||
};
|
||||
|
||||
let results1 = run(42);
|
||||
let results2 = run(42);
|
||||
assert_eq!(results1, results2, "same seed should produce same results");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn different_seeds_different_results() {
|
||||
let x = FloatParam::new(-5.0, 5.0).name("x");
|
||||
let y = FloatParam::new(-5.0, 5.0).name("y");
|
||||
|
||||
let run = |seed: u64| {
|
||||
let sampler = CmaEsSampler::with_seed(seed);
|
||||
let study: Study<f64> = Study::with_sampler(Direction::Minimize, sampler);
|
||||
study
|
||||
.optimize(20, |trial| {
|
||||
let xv = x.suggest(trial)?;
|
||||
let yv = y.suggest(trial)?;
|
||||
Ok::<_, Error>(xv * xv + yv * yv)
|
||||
})
|
||||
.unwrap();
|
||||
study.trials().iter().map(|t| t.value).collect::<Vec<_>>()
|
||||
};
|
||||
|
||||
let results1 = run(42);
|
||||
let results2 = run(99);
|
||||
assert_ne!(
|
||||
results1, results2,
|
||||
"different seeds should produce different results"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn single_dimension() {
|
||||
let sampler = CmaEsSampler::with_seed(42);
|
||||
let study: Study<f64> = Study::with_sampler(Direction::Minimize, sampler);
|
||||
|
||||
let x = FloatParam::new(-10.0, 10.0).name("x");
|
||||
|
||||
study
|
||||
.optimize(100, |trial| {
|
||||
let xv = x.suggest(trial)?;
|
||||
Ok::<_, Error>((xv - 3.0).powi(2))
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let best = study.best_trial().unwrap();
|
||||
assert!(
|
||||
best.value < 1.0,
|
||||
"1-D optimization should converge, got {}",
|
||||
best.value
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn integer_params() {
|
||||
let sampler = CmaEsSampler::with_seed(42);
|
||||
let study: Study<f64> = Study::with_sampler(Direction::Minimize, sampler);
|
||||
|
||||
let n = IntParam::new(1, 20).name("n");
|
||||
|
||||
study
|
||||
.optimize(100, |trial| {
|
||||
let nv = n.suggest(trial)?;
|
||||
// Minimum at n = 10
|
||||
Ok::<_, Error>(((nv - 10) * (nv - 10)) as f64)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let best = study.best_trial().unwrap();
|
||||
let best_n: i64 = best.get(&n).unwrap();
|
||||
assert!(
|
||||
(1..=20).contains(&best_n),
|
||||
"integer value {best_n} out of bounds"
|
||||
);
|
||||
assert!(
|
||||
best.value < 10.0,
|
||||
"integer optimization should converge, got {}",
|
||||
best.value
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn log_scale_params() {
|
||||
let sampler = CmaEsSampler::with_seed(42);
|
||||
let study: Study<f64> = Study::with_sampler(Direction::Minimize, sampler);
|
||||
|
||||
let lr = FloatParam::new(1e-5, 1.0).log_scale().name("lr");
|
||||
|
||||
study
|
||||
.optimize(100, |trial| {
|
||||
let lrv = lr.suggest(trial)?;
|
||||
// Minimum at lr = 0.01
|
||||
Ok::<_, Error>((lrv.ln() - 0.01_f64.ln()).powi(2))
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
for trial in study.trials() {
|
||||
let lrv: f64 = trial.get(&lr).unwrap();
|
||||
assert!(
|
||||
(1e-5..=1.0).contains(&lrv),
|
||||
"log-scale value {lrv} out of bounds"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn custom_population_size_and_sigma() {
|
||||
let sampler = CmaEsSampler::builder()
|
||||
.sigma0(1.0)
|
||||
.population_size(10)
|
||||
.seed(42)
|
||||
.build();
|
||||
let study: Study<f64> = Study::with_sampler(Direction::Minimize, sampler);
|
||||
|
||||
let x = FloatParam::new(-5.0, 5.0).name("x");
|
||||
let y = FloatParam::new(-5.0, 5.0).name("y");
|
||||
|
||||
study
|
||||
.optimize(100, |trial| {
|
||||
let xv = x.suggest(trial)?;
|
||||
let yv = y.suggest(trial)?;
|
||||
Ok::<_, Error>(xv * xv + yv * yv)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let best = study.best_trial().unwrap();
|
||||
assert!(
|
||||
best.value < 5.0,
|
||||
"custom config optimization should work, got {}",
|
||||
best.value
|
||||
);
|
||||
}
|
||||
@@ -0,0 +1,166 @@
|
||||
use optimizer::parameter::{CategoricalParam, FloatParam, IntParam, Parameter};
|
||||
use optimizer::{Direction, Study};
|
||||
|
||||
#[test]
|
||||
fn known_perfect_correlation() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(0.0, 100.0).name("x");
|
||||
|
||||
// Objective = x, so perfect correlation.
|
||||
for _ in 0..30 {
|
||||
let mut trial = study.ask();
|
||||
let xv = x.suggest(&mut trial).unwrap();
|
||||
study.tell(trial, Ok::<_, &str>(xv));
|
||||
}
|
||||
|
||||
let importance = study.param_importance();
|
||||
assert_eq!(importance.len(), 1);
|
||||
assert_eq!(importance[0].0, "x");
|
||||
assert!(
|
||||
(importance[0].1 - 1.0).abs() < 1e-10,
|
||||
"single param should be 1.0"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn no_effect_parameter() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(0.0, 100.0).name("x");
|
||||
let noise = FloatParam::new(0.0, 100.0).name("noise");
|
||||
|
||||
// Objective depends only on x; noise is unused in objective.
|
||||
for _ in 0..50 {
|
||||
let mut trial = study.ask();
|
||||
let xv = x.suggest(&mut trial).unwrap();
|
||||
let _nv = noise.suggest(&mut trial).unwrap();
|
||||
study.tell(trial, Ok::<_, &str>(xv));
|
||||
}
|
||||
|
||||
let importance = study.param_importance();
|
||||
assert_eq!(importance.len(), 2);
|
||||
// x should have much higher importance than noise.
|
||||
let x_score = importance.iter().find(|(l, _)| l == "x").unwrap().1;
|
||||
let noise_score = importance.iter().find(|(l, _)| l == "noise").unwrap().1;
|
||||
assert!(
|
||||
x_score > noise_score,
|
||||
"x ({x_score}) should outrank noise ({noise_score})"
|
||||
);
|
||||
// x should dominate
|
||||
assert!(x_score > 0.7, "x importance {x_score} should be dominant");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn multiple_parameters_varying_importance() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(0.0, 10.0).name("x");
|
||||
let y = FloatParam::new(0.0, 10.0).name("y");
|
||||
|
||||
// Objective = 10*x + 0.01*y → x should be far more important.
|
||||
for _ in 0..50 {
|
||||
let mut trial = study.ask();
|
||||
let xv = x.suggest(&mut trial).unwrap();
|
||||
let yv = y.suggest(&mut trial).unwrap();
|
||||
study.tell(trial, Ok::<_, &str>(10.0 * xv + 0.01 * yv));
|
||||
}
|
||||
|
||||
let importance = study.param_importance();
|
||||
assert_eq!(importance.len(), 2);
|
||||
assert_eq!(importance[0].0, "x", "x should rank first");
|
||||
assert!(importance[0].1 > importance[1].1);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn fewer_than_two_trials_returns_empty() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
|
||||
// 0 trials
|
||||
assert!(study.param_importance().is_empty());
|
||||
|
||||
// 1 trial
|
||||
let x = FloatParam::new(0.0, 1.0).name("x");
|
||||
let mut trial = study.ask();
|
||||
let xv = x.suggest(&mut trial).unwrap();
|
||||
study.tell(trial, Ok::<_, &str>(xv));
|
||||
assert!(study.param_importance().is_empty());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn int_parameter() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let n = IntParam::new(1, 100).name("n");
|
||||
|
||||
for _ in 0..30 {
|
||||
let mut trial = study.ask();
|
||||
let nv = n.suggest(&mut trial).unwrap();
|
||||
study.tell(trial, Ok::<_, &str>(nv as f64));
|
||||
}
|
||||
|
||||
let importance = study.param_importance();
|
||||
assert_eq!(importance.len(), 1);
|
||||
assert_eq!(importance[0].0, "n");
|
||||
assert!(importance[0].1 > 0.9);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn categorical_parameter() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let cat = CategoricalParam::new(vec!["a", "b", "c"]).name("cat");
|
||||
let x = FloatParam::new(0.0, 100.0).name("x");
|
||||
|
||||
// Objective depends only on x; categorical is random noise.
|
||||
for _ in 0..50 {
|
||||
let mut trial = study.ask();
|
||||
let _c = cat.suggest(&mut trial).unwrap();
|
||||
let xv = x.suggest(&mut trial).unwrap();
|
||||
study.tell(trial, Ok::<_, &str>(xv));
|
||||
}
|
||||
|
||||
let importance = study.param_importance();
|
||||
assert_eq!(importance.len(), 2);
|
||||
let x_score = importance.iter().find(|(l, _)| l == "x").unwrap().1;
|
||||
assert!(x_score > 0.5, "x should dominate over categorical noise");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn normalization_sums_to_one() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(0.0, 10.0).name("x");
|
||||
let y = FloatParam::new(0.0, 10.0).name("y");
|
||||
let z = FloatParam::new(0.0, 10.0).name("z");
|
||||
|
||||
for _ in 0..50 {
|
||||
let mut trial = study.ask();
|
||||
let xv = x.suggest(&mut trial).unwrap();
|
||||
let yv = y.suggest(&mut trial).unwrap();
|
||||
let zv = z.suggest(&mut trial).unwrap();
|
||||
study.tell(trial, Ok::<_, &str>(xv + 0.5 * yv + 0.1 * zv));
|
||||
}
|
||||
|
||||
let importance = study.param_importance();
|
||||
let sum: f64 = importance.iter().map(|(_, s)| *s).sum();
|
||||
assert!(
|
||||
(sum - 1.0).abs() < 1e-10,
|
||||
"scores should sum to 1.0, got {sum}"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn label_when_unnamed_uses_debug() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
// No .name() call → label defaults to Debug representation.
|
||||
let x = FloatParam::new(0.0, 10.0);
|
||||
|
||||
for _ in 0..10 {
|
||||
let mut trial = study.ask();
|
||||
let xv = x.suggest(&mut trial).unwrap();
|
||||
study.tell(trial, Ok::<_, &str>(xv));
|
||||
}
|
||||
|
||||
let importance = study.param_importance();
|
||||
assert_eq!(importance.len(), 1);
|
||||
assert!(
|
||||
importance[0].0.starts_with("FloatParam"),
|
||||
"expected Debug label, got {:?}",
|
||||
importance[0].0
|
||||
);
|
||||
}
|
||||
@@ -1363,3 +1363,885 @@ fn test_completed_trial_get() {
|
||||
assert!((-10.0..=10.0).contains(&x_val));
|
||||
assert!((1..=10).contains(&n_val));
|
||||
}
|
||||
|
||||
// =============================================================================
|
||||
// Tests for timeout-based optimization
|
||||
// =============================================================================
|
||||
|
||||
#[test]
|
||||
fn test_optimize_until_runs_for_approximately_specified_duration() {
|
||||
use std::time::{Duration, Instant};
|
||||
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x_param = FloatParam::new(-10.0, 10.0);
|
||||
|
||||
let duration = Duration::from_millis(200);
|
||||
let start = Instant::now();
|
||||
|
||||
study
|
||||
.optimize_until(duration, |trial| {
|
||||
let x = x_param.suggest(trial)?;
|
||||
Ok::<_, Error>(x * x)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let elapsed = start.elapsed();
|
||||
assert!(
|
||||
elapsed >= duration,
|
||||
"should run for at least the specified duration, elapsed: {elapsed:?}"
|
||||
);
|
||||
// Allow generous upper bound — the last trial may overshoot
|
||||
assert!(
|
||||
elapsed < duration + Duration::from_millis(200),
|
||||
"should not overshoot excessively, elapsed: {elapsed:?}"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_optimize_until_completes_at_least_one_trial() {
|
||||
use std::time::Duration;
|
||||
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x_param = FloatParam::new(-10.0, 10.0);
|
||||
|
||||
study
|
||||
.optimize_until(Duration::from_millis(100), |trial| {
|
||||
let x = x_param.suggest(trial)?;
|
||||
Ok::<_, Error>(x * x)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
assert!(
|
||||
study.n_trials() >= 1,
|
||||
"should complete at least one trial, got {}",
|
||||
study.n_trials()
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_optimize_until_works_with_minimize() {
|
||||
use std::time::Duration;
|
||||
|
||||
let sampler = RandomSampler::with_seed(42);
|
||||
let study: Study<f64> = Study::with_sampler(Direction::Minimize, sampler);
|
||||
let x_param = FloatParam::new(-10.0, 10.0);
|
||||
|
||||
study
|
||||
.optimize_until(Duration::from_millis(100), |trial| {
|
||||
let x = x_param.suggest(trial)?;
|
||||
Ok::<_, Error>(x * x)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let best = study.best_value().unwrap();
|
||||
assert!(best >= 0.0, "x^2 should be non-negative");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_optimize_until_works_with_maximize() {
|
||||
use std::time::Duration;
|
||||
|
||||
let sampler = RandomSampler::with_seed(42);
|
||||
let study: Study<f64> = Study::with_sampler(Direction::Maximize, sampler);
|
||||
let x_param = FloatParam::new(0.0, 10.0);
|
||||
|
||||
study
|
||||
.optimize_until(Duration::from_millis(100), |trial| {
|
||||
let x = x_param.suggest(trial)?;
|
||||
Ok::<_, Error>(x)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let best = study.best_value().unwrap();
|
||||
assert!(best >= 0.0);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_optimize_until_with_callback_early_stopping() {
|
||||
use std::ops::ControlFlow;
|
||||
use std::time::Duration;
|
||||
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x_param = FloatParam::new(0.0, 10.0);
|
||||
|
||||
study
|
||||
.optimize_until_with_callback(
|
||||
Duration::from_secs(10), // long timeout — callback should stop early
|
||||
|trial| {
|
||||
let x = x_param.suggest(trial)?;
|
||||
Ok::<_, Error>(x)
|
||||
},
|
||||
|study, _trial| {
|
||||
if study.n_trials() >= 5 {
|
||||
ControlFlow::Break(())
|
||||
} else {
|
||||
ControlFlow::Continue(())
|
||||
}
|
||||
},
|
||||
)
|
||||
.unwrap();
|
||||
|
||||
assert_eq!(
|
||||
study.n_trials(),
|
||||
5,
|
||||
"callback should have stopped after 5 trials"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_optimize_until_all_trials_fail() {
|
||||
use std::time::Duration;
|
||||
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
|
||||
let result = study.optimize_until(Duration::from_millis(50), |_trial| {
|
||||
Err::<f64, &str>("always fails")
|
||||
});
|
||||
|
||||
assert!(
|
||||
matches!(result, Err(Error::NoCompletedTrials)),
|
||||
"should return NoCompletedTrials when all trials fail"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_optimize_until_with_non_f64_value_type() {
|
||||
use std::time::Duration;
|
||||
|
||||
let study: Study<i32> = Study::new(Direction::Minimize);
|
||||
let x_param = IntParam::new(-10, 10);
|
||||
|
||||
study
|
||||
.optimize_until(Duration::from_millis(100), |trial| {
|
||||
let x = x_param.suggest(trial)?;
|
||||
Ok::<_, Error>(x.abs() as i32)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
assert!(study.n_trials() >= 1);
|
||||
let best = study.best_trial().unwrap();
|
||||
assert!(best.value >= 0);
|
||||
}
|
||||
|
||||
// =============================================================================
|
||||
// Tests for top_trials
|
||||
// =============================================================================
|
||||
|
||||
#[test]
|
||||
fn test_top_trials_minimize() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
|
||||
// Manually complete trials with known values
|
||||
for &val in &[5.0, 1.0, 3.0, 2.0, 4.0] {
|
||||
let trial = study.create_trial();
|
||||
study.complete_trial(trial, val);
|
||||
}
|
||||
|
||||
let top3 = study.top_trials(3);
|
||||
assert_eq!(top3.len(), 3);
|
||||
assert_eq!(top3[0].value, 1.0);
|
||||
assert_eq!(top3[1].value, 2.0);
|
||||
assert_eq!(top3[2].value, 3.0);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_top_trials_maximize() {
|
||||
let study: Study<f64> = Study::new(Direction::Maximize);
|
||||
|
||||
for &val in &[5.0, 1.0, 3.0, 2.0, 4.0] {
|
||||
let trial = study.create_trial();
|
||||
study.complete_trial(trial, val);
|
||||
}
|
||||
|
||||
let top3 = study.top_trials(3);
|
||||
assert_eq!(top3.len(), 3);
|
||||
assert_eq!(top3[0].value, 5.0);
|
||||
assert_eq!(top3[1].value, 4.0);
|
||||
assert_eq!(top3[2].value, 3.0);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_top_trials_n_greater_than_total() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
|
||||
for &val in &[3.0, 1.0] {
|
||||
let trial = study.create_trial();
|
||||
study.complete_trial(trial, val);
|
||||
}
|
||||
|
||||
let top = study.top_trials(10);
|
||||
assert_eq!(top.len(), 2);
|
||||
assert_eq!(top[0].value, 1.0);
|
||||
assert_eq!(top[1].value, 3.0);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_top_trials_empty() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
|
||||
let top = study.top_trials(5);
|
||||
assert!(top.is_empty());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_top_trials_excludes_pruned() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
|
||||
// Complete some trials
|
||||
for &val in &[5.0, 1.0, 3.0] {
|
||||
let trial = study.create_trial();
|
||||
study.complete_trial(trial, val);
|
||||
}
|
||||
|
||||
// Prune a trial (it gets a default value of 0.0 but should be excluded)
|
||||
let trial = study.create_trial();
|
||||
study.prune_trial(trial);
|
||||
|
||||
let top = study.top_trials(5);
|
||||
assert_eq!(top.len(), 3, "pruned trial should be excluded");
|
||||
assert_eq!(top[0].value, 1.0);
|
||||
}
|
||||
|
||||
// =============================================================================
|
||||
// Test: ask-and-tell interface
|
||||
// =============================================================================
|
||||
|
||||
#[test]
|
||||
fn test_ask_and_tell_basic() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x_param = FloatParam::new(0.0, 10.0);
|
||||
|
||||
for _ in 0..10 {
|
||||
let mut trial = study.ask();
|
||||
let x = x_param.suggest(&mut trial).unwrap();
|
||||
let value = x * x;
|
||||
study.tell(trial, Ok::<_, &str>(value));
|
||||
}
|
||||
|
||||
assert_eq!(study.n_trials(), 10);
|
||||
assert!(study.best_value().unwrap() >= 0.0);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_ask_and_tell_with_failures() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x_param = FloatParam::new(-5.0, 5.0);
|
||||
|
||||
// Alternate success and failure
|
||||
for i in 0..10 {
|
||||
let mut trial = study.ask();
|
||||
let x = x_param.suggest(&mut trial).unwrap();
|
||||
if i % 2 == 0 {
|
||||
study.tell(trial, Ok::<_, &str>(x * x));
|
||||
} else {
|
||||
study.tell(trial, Err::<f64, _>("simulated failure"));
|
||||
}
|
||||
}
|
||||
|
||||
// Only successful trials are counted
|
||||
assert_eq!(study.n_trials(), 5);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_ask_and_tell_with_tpe_sampler() {
|
||||
let sampler = TpeSampler::builder()
|
||||
.seed(42)
|
||||
.n_startup_trials(5)
|
||||
.build()
|
||||
.unwrap();
|
||||
let study: Study<f64> = Study::minimize(sampler);
|
||||
let x_param = FloatParam::new(-10.0, 10.0);
|
||||
|
||||
for _ in 0..30 {
|
||||
let mut trial = study.ask();
|
||||
let x = x_param.suggest(&mut trial).unwrap();
|
||||
study.tell(trial, Ok::<_, &str>((x - 3.0).powi(2)));
|
||||
}
|
||||
|
||||
assert_eq!(study.n_trials(), 30);
|
||||
assert!(
|
||||
study.best_value().unwrap() < 5.0,
|
||||
"TPE ask-and-tell should find a reasonable value"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_ask_and_tell_batch() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x_param = FloatParam::new(0.0, 10.0);
|
||||
|
||||
// Ask a batch of trials
|
||||
let batch: Vec<_> = (0..5)
|
||||
.map(|_| {
|
||||
let mut t = study.ask();
|
||||
let x = x_param.suggest(&mut t).unwrap();
|
||||
(t, x)
|
||||
})
|
||||
.collect();
|
||||
|
||||
// Tell results for the batch
|
||||
for (trial, x) in batch {
|
||||
study.tell(trial, Ok::<_, &str>(x * x));
|
||||
}
|
||||
|
||||
assert_eq!(study.n_trials(), 5);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_ask_and_tell_with_custom_value_type() {
|
||||
// Ask-and-tell works with non-f64 value types too
|
||||
let study: Study<i32> = Study::new(Direction::Maximize);
|
||||
|
||||
for i in 0..5 {
|
||||
let trial = study.ask();
|
||||
study.tell(trial, Ok::<_, &str>(i * 10));
|
||||
}
|
||||
|
||||
assert_eq!(study.n_trials(), 5);
|
||||
assert_eq!(study.best_value().unwrap(), 40);
|
||||
}
|
||||
|
||||
// =============================================================================
|
||||
// Tests: enqueue trials
|
||||
// =============================================================================
|
||||
|
||||
use std::collections::HashMap;
|
||||
|
||||
use optimizer::ParamValue;
|
||||
|
||||
#[test]
|
||||
fn test_enqueue_params_evaluated_first() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(0.0, 10.0);
|
||||
let y = IntParam::new(1, 100);
|
||||
|
||||
// Enqueue a specific configuration
|
||||
study.enqueue(HashMap::from([
|
||||
(x.id(), ParamValue::Float(5.0)),
|
||||
(y.id(), ParamValue::Int(42)),
|
||||
]));
|
||||
|
||||
// The first trial should use the enqueued params
|
||||
let mut trial = study.ask();
|
||||
let x_val = x.suggest(&mut trial).unwrap();
|
||||
let y_val = y.suggest(&mut trial).unwrap();
|
||||
|
||||
assert_eq!(x_val, 5.0);
|
||||
assert_eq!(y_val, 42);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_enqueue_fifo_order() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(0.0, 10.0);
|
||||
|
||||
// Enqueue two configs
|
||||
study.enqueue(HashMap::from([(x.id(), ParamValue::Float(1.0))]));
|
||||
study.enqueue(HashMap::from([(x.id(), ParamValue::Float(2.0))]));
|
||||
|
||||
// First trial gets first enqueued value
|
||||
let mut trial1 = study.ask();
|
||||
assert_eq!(x.suggest(&mut trial1).unwrap(), 1.0);
|
||||
|
||||
// Second trial gets second enqueued value
|
||||
let mut trial2 = study.ask();
|
||||
assert_eq!(x.suggest(&mut trial2).unwrap(), 2.0);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_enqueue_then_normal_sampling_resumes() {
|
||||
let sampler = RandomSampler::with_seed(42);
|
||||
let study: Study<f64> = Study::with_sampler(Direction::Minimize, sampler);
|
||||
let x = FloatParam::new(0.0, 10.0);
|
||||
|
||||
// Enqueue one config
|
||||
study.enqueue(HashMap::from([(x.id(), ParamValue::Float(5.0))]));
|
||||
|
||||
// First trial uses enqueued value
|
||||
let mut trial1 = study.ask();
|
||||
assert_eq!(x.suggest(&mut trial1).unwrap(), 5.0);
|
||||
study.tell(trial1, Ok::<_, &str>(25.0));
|
||||
|
||||
// Second trial uses normal sampling (not 5.0)
|
||||
let mut trial2 = study.ask();
|
||||
let x_val = x.suggest(&mut trial2).unwrap();
|
||||
// The sampled value should be in [0, 10] but extremely unlikely to be exactly 5.0
|
||||
assert!((0.0..=10.0).contains(&x_val));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_enqueue_with_optimize() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(0.0, 10.0);
|
||||
|
||||
// Enqueue two specific configs
|
||||
study.enqueue(HashMap::from([(x.id(), ParamValue::Float(1.0))]));
|
||||
study.enqueue(HashMap::from([(x.id(), ParamValue::Float(2.0))]));
|
||||
|
||||
let mut values = Vec::new();
|
||||
|
||||
study
|
||||
.optimize(5, |trial| {
|
||||
let x_val = x.suggest(trial)?;
|
||||
values.push(x_val);
|
||||
Ok::<_, Error>(x_val * x_val)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
// First two trials should use enqueued values
|
||||
assert_eq!(values[0], 1.0);
|
||||
assert_eq!(values[1], 2.0);
|
||||
// All 5 trials should have completed
|
||||
assert_eq!(study.n_trials(), 5);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_enqueue_partial_params_fall_back_to_sampling() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(0.0, 10.0);
|
||||
let y = IntParam::new(1, 100);
|
||||
|
||||
// Enqueue only x, not y
|
||||
study.enqueue(HashMap::from([(x.id(), ParamValue::Float(3.0))]));
|
||||
|
||||
let mut trial = study.ask();
|
||||
let x_val = x.suggest(&mut trial).unwrap();
|
||||
let y_val = y.suggest(&mut trial).unwrap();
|
||||
|
||||
// x should be the enqueued value
|
||||
assert_eq!(x_val, 3.0);
|
||||
// y should be sampled (within range)
|
||||
assert!((1..=100).contains(&y_val));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_enqueue_trials_appear_in_completed_trials() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(0.0, 10.0);
|
||||
|
||||
study.enqueue(HashMap::from([(x.id(), ParamValue::Float(7.0))]));
|
||||
|
||||
study
|
||||
.optimize(1, |trial| {
|
||||
let x_val = x.suggest(trial)?;
|
||||
Ok::<_, Error>(x_val)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let trials = study.trials();
|
||||
assert_eq!(trials.len(), 1);
|
||||
assert_eq!(trials[0].value, 7.0);
|
||||
assert_eq!(
|
||||
*trials[0].params.get(&x.id()).unwrap(),
|
||||
ParamValue::Float(7.0)
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_enqueue_with_ask_and_tell() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(0.0, 10.0);
|
||||
|
||||
study.enqueue(HashMap::from([(x.id(), ParamValue::Float(4.0))]));
|
||||
|
||||
let mut trial = study.ask();
|
||||
let x_val = x.suggest(&mut trial).unwrap();
|
||||
assert_eq!(x_val, 4.0);
|
||||
|
||||
study.tell(trial, Ok::<_, &str>(x_val * x_val));
|
||||
assert_eq!(study.n_trials(), 1);
|
||||
assert_eq!(study.best_value().unwrap(), 16.0);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_n_enqueued() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(0.0, 10.0);
|
||||
|
||||
assert_eq!(study.n_enqueued(), 0);
|
||||
|
||||
study.enqueue(HashMap::from([(x.id(), ParamValue::Float(1.0))]));
|
||||
assert_eq!(study.n_enqueued(), 1);
|
||||
|
||||
study.enqueue(HashMap::from([(x.id(), ParamValue::Float(2.0))]));
|
||||
assert_eq!(study.n_enqueued(), 2);
|
||||
|
||||
// Creating a trial dequeues one
|
||||
let _ = study.ask();
|
||||
assert_eq!(study.n_enqueued(), 1);
|
||||
|
||||
let _ = study.ask();
|
||||
assert_eq!(study.n_enqueued(), 0);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_enqueue_counted_in_n_trials() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(0.0, 10.0);
|
||||
|
||||
study.enqueue(HashMap::from([(x.id(), ParamValue::Float(1.0))]));
|
||||
study.enqueue(HashMap::from([(x.id(), ParamValue::Float(2.0))]));
|
||||
|
||||
study
|
||||
.optimize(5, |trial| {
|
||||
let x_val = x.suggest(trial)?;
|
||||
Ok::<_, Error>(x_val)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
// All 5 trials count, including the 2 enqueued ones
|
||||
assert_eq!(study.n_trials(), 5);
|
||||
}
|
||||
|
||||
// =============================================================================
|
||||
// Test: Study summary and Display
|
||||
// =============================================================================
|
||||
|
||||
#[test]
|
||||
fn test_summary_with_completed_trials() {
|
||||
let study: Study<f64> = Study::with_sampler(Direction::Minimize, RandomSampler::with_seed(1));
|
||||
let x = FloatParam::new(0.0, 10.0).name("x");
|
||||
|
||||
study
|
||||
.optimize(5, |trial| {
|
||||
let val = x.suggest(trial)?;
|
||||
Ok::<_, Error>(val * val)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let summary = study.summary();
|
||||
assert!(summary.contains("Minimize"));
|
||||
assert!(summary.contains("5 trials"));
|
||||
assert!(summary.contains("Best value:"));
|
||||
assert!(summary.contains("x = "));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_summary_no_completed_trials() {
|
||||
let study: Study<f64> = Study::new(Direction::Maximize);
|
||||
let summary = study.summary();
|
||||
assert!(summary.contains("Maximize"));
|
||||
assert!(summary.contains("0 trials"));
|
||||
assert!(!summary.contains("Best value:"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_summary_with_pruned_trials() {
|
||||
let study: Study<f64> = Study::with_sampler(Direction::Minimize, RandomSampler::with_seed(1));
|
||||
let x = FloatParam::new(0.0, 10.0).name("x");
|
||||
|
||||
// Manually create some complete and pruned trials
|
||||
for _ in 0..3 {
|
||||
let mut trial = study.create_trial();
|
||||
let val = x.suggest(&mut trial).unwrap();
|
||||
study.complete_trial(trial, val);
|
||||
}
|
||||
for _ in 0..2 {
|
||||
let mut trial = study.create_trial();
|
||||
let _ = x.suggest(&mut trial).unwrap();
|
||||
study.prune_trial(trial);
|
||||
}
|
||||
|
||||
let summary = study.summary();
|
||||
// Should show breakdown when there are pruned trials
|
||||
if study.n_pruned_trials() > 0 {
|
||||
assert!(summary.contains("complete"));
|
||||
assert!(summary.contains("pruned"));
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_display_matches_summary() {
|
||||
let study: Study<f64> = Study::with_sampler(Direction::Minimize, RandomSampler::with_seed(1));
|
||||
let x = FloatParam::new(0.0, 10.0).name("x");
|
||||
|
||||
study
|
||||
.optimize(3, |trial| {
|
||||
let val = x.suggest(trial)?;
|
||||
Ok::<_, Error>(val)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
assert_eq!(format!("{study}"), study.summary());
|
||||
}
|
||||
|
||||
// =============================================================================
|
||||
// Tests: optimize_with_retries
|
||||
// =============================================================================
|
||||
|
||||
#[test]
|
||||
fn test_retries_successful_trials_not_retried() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x_param = FloatParam::new(0.0, 10.0);
|
||||
let call_count = std::cell::Cell::new(0u32);
|
||||
|
||||
study
|
||||
.optimize_with_retries(5, 3, |trial| {
|
||||
let x = x_param.suggest(trial)?;
|
||||
call_count.set(call_count.get() + 1);
|
||||
Ok::<_, Error>(x * x)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
// All trials succeed on first try — exactly 5 calls
|
||||
assert_eq!(call_count.get(), 5);
|
||||
assert_eq!(study.n_trials(), 5);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_retries_failed_trials_retried_up_to_max() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x_param = FloatParam::new(0.0, 10.0);
|
||||
let call_count = std::cell::Cell::new(0u32);
|
||||
|
||||
let result = study.optimize_with_retries(1, 3, |trial| {
|
||||
let _ = x_param.suggest(trial).unwrap();
|
||||
call_count.set(call_count.get() + 1);
|
||||
Err::<f64, _>("always fails")
|
||||
});
|
||||
|
||||
// 1 initial attempt + 3 retries = 4 total calls
|
||||
assert_eq!(call_count.get(), 4);
|
||||
// No trials completed
|
||||
assert!(matches!(result, Err(Error::NoCompletedTrials)));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_retries_permanently_failed_after_exhaustion() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x_param = FloatParam::new(0.0, 10.0);
|
||||
|
||||
let result = study.optimize_with_retries(3, 2, |trial| {
|
||||
let _ = x_param.suggest(trial).unwrap();
|
||||
Err::<f64, _>("transient error")
|
||||
});
|
||||
|
||||
assert!(
|
||||
matches!(result, Err(Error::NoCompletedTrials)),
|
||||
"all trials should permanently fail"
|
||||
);
|
||||
assert_eq!(
|
||||
study.n_trials(),
|
||||
0,
|
||||
"no completed trials should be recorded"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_retries_uses_same_parameters() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x_param = FloatParam::new(0.0, 10.0);
|
||||
let seen_values = std::cell::RefCell::new(Vec::new());
|
||||
let call_count = std::cell::Cell::new(0u32);
|
||||
|
||||
study
|
||||
.optimize_with_retries(1, 2, |trial| {
|
||||
let x = x_param.suggest(trial).map_err(|e| e.to_string())?;
|
||||
seen_values.borrow_mut().push(x);
|
||||
call_count.set(call_count.get() + 1);
|
||||
// Fail first two attempts, succeed on third
|
||||
if call_count.get() < 3 {
|
||||
Err::<f64, _>("transient".to_string())
|
||||
} else {
|
||||
Ok(x * x)
|
||||
}
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let values = seen_values.borrow();
|
||||
assert_eq!(values.len(), 3, "should be called 3 times (1 + 2 retries)");
|
||||
// All three calls should have gotten the same parameter value
|
||||
assert_eq!(values[0], values[1]);
|
||||
assert_eq!(values[1], values[2]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_retries_n_trials_counts_unique_configs() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x_param = FloatParam::new(0.0, 10.0);
|
||||
let call_count = std::cell::Cell::new(0u32);
|
||||
|
||||
study
|
||||
.optimize_with_retries(3, 2, |trial| {
|
||||
let x = x_param.suggest(trial).map_err(|e| e.to_string())?;
|
||||
call_count.set(call_count.get() + 1);
|
||||
// Fail first attempt of each config, succeed on retry
|
||||
if call_count.get() % 2 == 1 {
|
||||
Err::<f64, _>("transient".to_string())
|
||||
} else {
|
||||
Ok(x * x)
|
||||
}
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
// 3 unique configs, each needing 2 calls = 6 total calls
|
||||
assert_eq!(call_count.get(), 6);
|
||||
// But only 3 completed trials
|
||||
assert_eq!(study.n_trials(), 3);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_retries_with_zero_max_retries_same_as_optimize() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x_param = FloatParam::new(0.0, 10.0);
|
||||
let call_count = std::cell::Cell::new(0u32);
|
||||
|
||||
study
|
||||
.optimize_with_retries(5, 0, |trial| {
|
||||
let x = x_param.suggest(trial)?;
|
||||
call_count.set(call_count.get() + 1);
|
||||
Ok::<_, Error>(x * x)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
assert_eq!(call_count.get(), 5);
|
||||
assert_eq!(study.n_trials(), 5);
|
||||
}
|
||||
|
||||
// =============================================================================
|
||||
// Tests: IntoIterator for &Study
|
||||
// =============================================================================
|
||||
|
||||
#[test]
|
||||
fn test_into_iterator_iterates_all_trials() {
|
||||
let study: Study<f64> = Study::with_sampler(Direction::Minimize, RandomSampler::with_seed(42));
|
||||
let x_param = FloatParam::new(0.0, 10.0);
|
||||
|
||||
for _ in 0..5 {
|
||||
let mut trial = study.create_trial();
|
||||
let x = x_param.suggest(&mut trial).unwrap();
|
||||
study.complete_trial(trial, x * x);
|
||||
}
|
||||
|
||||
let mut count = 0;
|
||||
for trial in &study {
|
||||
assert_eq!(trial.state, optimizer::TrialState::Complete);
|
||||
count += 1;
|
||||
}
|
||||
assert_eq!(count, 5);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_into_iterator_empty_study() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
|
||||
let count = (&study).into_iter().count();
|
||||
assert_eq!(count, 0);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_into_iterator_preserves_insertion_order() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
|
||||
for i in 0..3 {
|
||||
let trial = study.create_trial();
|
||||
study.complete_trial(trial, f64::from(i));
|
||||
}
|
||||
|
||||
let ids: Vec<u64> = (&study).into_iter().map(|t| t.id).collect();
|
||||
assert_eq!(ids, vec![0, 1, 2]);
|
||||
}
|
||||
|
||||
// =============================================================================
|
||||
// Tests: Constraint handling
|
||||
// =============================================================================
|
||||
|
||||
#[test]
|
||||
fn test_is_feasible_all_satisfied() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let mut trial = study.create_trial();
|
||||
trial.set_constraints(vec![-1.0, 0.0, -0.5]);
|
||||
study.complete_trial(trial, 1.0);
|
||||
|
||||
let completed = study.best_trial().unwrap();
|
||||
assert!(completed.is_feasible());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_is_feasible_one_violated() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let mut trial = study.create_trial();
|
||||
trial.set_constraints(vec![-1.0, 0.5, -0.5]);
|
||||
study.complete_trial(trial, 1.0);
|
||||
|
||||
let completed = study.best_trial().unwrap();
|
||||
assert!(!completed.is_feasible());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_is_feasible_empty_constraints() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let trial = study.create_trial();
|
||||
study.complete_trial(trial, 1.0);
|
||||
|
||||
let completed = study.best_trial().unwrap();
|
||||
assert!(completed.is_feasible());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_best_trial_prefers_feasible() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
|
||||
// Infeasible trial with better objective
|
||||
let mut trial1 = study.create_trial();
|
||||
trial1.set_constraints(vec![1.0]);
|
||||
study.complete_trial(trial1, 0.1);
|
||||
|
||||
// Feasible trial with worse objective
|
||||
let mut trial2 = study.create_trial();
|
||||
trial2.set_constraints(vec![-1.0]);
|
||||
study.complete_trial(trial2, 100.0);
|
||||
|
||||
let best = study.best_trial().unwrap();
|
||||
assert_eq!(best.id, 1); // feasible trial wins
|
||||
assert_eq!(best.value, 100.0);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_best_trial_feasible_by_objective() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
|
||||
// Feasible, worse objective
|
||||
let mut trial1 = study.create_trial();
|
||||
trial1.set_constraints(vec![-1.0]);
|
||||
study.complete_trial(trial1, 10.0);
|
||||
|
||||
// Feasible, better objective
|
||||
let mut trial2 = study.create_trial();
|
||||
trial2.set_constraints(vec![-0.5]);
|
||||
study.complete_trial(trial2, 2.0);
|
||||
|
||||
let best = study.best_trial().unwrap();
|
||||
assert_eq!(best.id, 1); // lower objective wins among feasible
|
||||
assert_eq!(best.value, 2.0);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_top_trials_ranks_feasible_above_infeasible() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
|
||||
// Infeasible, low violation
|
||||
let mut t0 = study.create_trial();
|
||||
t0.set_constraints(vec![0.5]);
|
||||
study.complete_trial(t0, 1.0);
|
||||
|
||||
// Feasible, worst objective among feasible
|
||||
let mut t1 = study.create_trial();
|
||||
t1.set_constraints(vec![-1.0]);
|
||||
study.complete_trial(t1, 50.0);
|
||||
|
||||
// Feasible, best objective among feasible
|
||||
let mut t2 = study.create_trial();
|
||||
t2.set_constraints(vec![-0.1]);
|
||||
study.complete_trial(t2, 5.0);
|
||||
|
||||
// Infeasible, high violation
|
||||
let mut t3 = study.create_trial();
|
||||
t3.set_constraints(vec![3.0]);
|
||||
study.complete_trial(t3, 0.5);
|
||||
|
||||
let top = study.top_trials(4);
|
||||
let ids: Vec<u64> = top.iter().map(|t| t.id).collect();
|
||||
// Feasible sorted by objective first (5.0, 50.0), then infeasible by violation (0.5, 3.0)
|
||||
assert_eq!(ids, vec![2, 1, 0, 3]);
|
||||
}
|
||||
|
||||
@@ -0,0 +1,228 @@
|
||||
use std::collections::HashMap;
|
||||
|
||||
use optimizer::Direction;
|
||||
use optimizer::pruner::{MedianPruner, Pruner};
|
||||
use optimizer::sampler::CompletedTrial;
|
||||
|
||||
/// Helper to build a completed trial with given intermediate values.
|
||||
fn trial_with_values(id: u64, intermediate_values: Vec<(u64, f64)>) -> CompletedTrial {
|
||||
CompletedTrial::with_intermediate_values(
|
||||
id,
|
||||
HashMap::new(),
|
||||
HashMap::new(),
|
||||
HashMap::new(),
|
||||
0.0,
|
||||
intermediate_values,
|
||||
HashMap::new(),
|
||||
)
|
||||
}
|
||||
|
||||
// --- Minimize direction ---
|
||||
|
||||
#[test]
|
||||
fn prune_when_worse_than_median_minimize() {
|
||||
let pruner = MedianPruner::new(Direction::Minimize);
|
||||
// 3 completed trials with values at step 2: [1.0, 2.0, 3.0] => median = 2.0
|
||||
let completed = vec![
|
||||
trial_with_values(0, vec![(0, 0.5), (1, 0.8), (2, 1.0)]),
|
||||
trial_with_values(1, vec![(0, 0.6), (1, 1.5), (2, 2.0)]),
|
||||
trial_with_values(2, vec![(0, 0.7), (1, 2.0), (2, 3.0)]),
|
||||
];
|
||||
// Current trial value at step 2 is 2.5 > median 2.0 => prune
|
||||
let current = vec![(0, 0.5), (1, 1.0), (2, 2.5)];
|
||||
assert!(pruner.should_prune(3, 2, ¤t, &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn no_prune_when_better_than_median_minimize() {
|
||||
let pruner = MedianPruner::new(Direction::Minimize);
|
||||
let completed = vec![
|
||||
trial_with_values(0, vec![(0, 0.5), (1, 0.8), (2, 1.0)]),
|
||||
trial_with_values(1, vec![(0, 0.6), (1, 1.5), (2, 2.0)]),
|
||||
trial_with_values(2, vec![(0, 0.7), (1, 2.0), (2, 3.0)]),
|
||||
];
|
||||
// Current trial value at step 2 is 1.5 < median 2.0 => don't prune
|
||||
let current = vec![(0, 0.5), (1, 1.0), (2, 1.5)];
|
||||
assert!(!pruner.should_prune(3, 2, ¤t, &completed));
|
||||
}
|
||||
|
||||
// --- Maximize direction ---
|
||||
|
||||
#[test]
|
||||
fn prune_when_worse_than_median_maximize() {
|
||||
let pruner = MedianPruner::new(Direction::Maximize);
|
||||
// Values at step 1: [5.0, 7.0, 9.0] => median = 7.0
|
||||
let completed = vec![
|
||||
trial_with_values(0, vec![(0, 3.0), (1, 5.0)]),
|
||||
trial_with_values(1, vec![(0, 4.0), (1, 7.0)]),
|
||||
trial_with_values(2, vec![(0, 5.0), (1, 9.0)]),
|
||||
];
|
||||
// Current value 6.0 < median 7.0 => prune (worse for maximize)
|
||||
let current = vec![(0, 4.0), (1, 6.0)];
|
||||
assert!(pruner.should_prune(3, 1, ¤t, &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn no_prune_when_better_than_median_maximize() {
|
||||
let pruner = MedianPruner::new(Direction::Maximize);
|
||||
let completed = vec![
|
||||
trial_with_values(0, vec![(0, 3.0), (1, 5.0)]),
|
||||
trial_with_values(1, vec![(0, 4.0), (1, 7.0)]),
|
||||
trial_with_values(2, vec![(0, 5.0), (1, 9.0)]),
|
||||
];
|
||||
// Current value 8.0 > median 7.0 => don't prune
|
||||
let current = vec![(0, 4.0), (1, 8.0)];
|
||||
assert!(!pruner.should_prune(3, 1, ¤t, &completed));
|
||||
}
|
||||
|
||||
// --- Warmup steps ---
|
||||
|
||||
#[test]
|
||||
fn no_prune_during_warmup() {
|
||||
let pruner = MedianPruner::new(Direction::Minimize).n_warmup_steps(5);
|
||||
let completed = vec![trial_with_values(0, vec![(0, 1.0), (1, 1.0), (2, 1.0)])];
|
||||
// Step 2 < warmup 5 => never prune, even if value is terrible
|
||||
let current = vec![(0, 100.0), (1, 100.0), (2, 100.0)];
|
||||
assert!(!pruner.should_prune(1, 2, ¤t, &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn prune_after_warmup() {
|
||||
let pruner = MedianPruner::new(Direction::Minimize).n_warmup_steps(2);
|
||||
let completed = vec![trial_with_values(0, vec![(0, 1.0), (1, 1.0), (2, 1.0)])];
|
||||
// Step 2 >= warmup 2 => pruning allowed; current 100.0 > median 1.0
|
||||
let current = vec![(0, 100.0), (1, 100.0), (2, 100.0)];
|
||||
assert!(pruner.should_prune(1, 2, ¤t, &completed));
|
||||
}
|
||||
|
||||
// --- n_min_trials ---
|
||||
|
||||
#[test]
|
||||
fn no_prune_when_fewer_than_n_min_trials() {
|
||||
let pruner = MedianPruner::new(Direction::Minimize).n_min_trials(3);
|
||||
// Only 2 completed trials — below threshold of 3
|
||||
let completed = vec![
|
||||
trial_with_values(0, vec![(0, 1.0)]),
|
||||
trial_with_values(1, vec![(0, 2.0)]),
|
||||
];
|
||||
let current = vec![(0, 100.0)];
|
||||
assert!(!pruner.should_prune(2, 0, ¤t, &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn prune_when_at_least_n_min_trials() {
|
||||
let pruner = MedianPruner::new(Direction::Minimize).n_min_trials(3);
|
||||
// 3 completed trials with step 0: [1.0, 2.0, 3.0] => median 2.0
|
||||
let completed = vec![
|
||||
trial_with_values(0, vec![(0, 1.0)]),
|
||||
trial_with_values(1, vec![(0, 2.0)]),
|
||||
trial_with_values(2, vec![(0, 3.0)]),
|
||||
];
|
||||
// 5.0 > median 2.0 => prune
|
||||
let current = vec![(0, 5.0)];
|
||||
assert!(pruner.should_prune(3, 0, ¤t, &completed));
|
||||
}
|
||||
|
||||
// --- No completed trials with values at step ---
|
||||
|
||||
#[test]
|
||||
fn no_prune_when_no_completed_trials_at_step() {
|
||||
let pruner = MedianPruner::new(Direction::Minimize);
|
||||
// Completed trials only have values at step 0, not step 5
|
||||
let completed = vec![
|
||||
trial_with_values(0, vec![(0, 1.0)]),
|
||||
trial_with_values(1, vec![(0, 2.0)]),
|
||||
];
|
||||
let current = vec![(0, 0.5), (5, 100.0)];
|
||||
assert!(!pruner.should_prune(2, 5, ¤t, &completed));
|
||||
}
|
||||
|
||||
// --- Median calculation edge cases ---
|
||||
|
||||
#[test]
|
||||
fn correct_median_with_even_number_of_trials() {
|
||||
let pruner = MedianPruner::new(Direction::Minimize);
|
||||
// 4 trials at step 0: [1.0, 2.0, 3.0, 4.0] => median = 2.5
|
||||
let completed = vec![
|
||||
trial_with_values(0, vec![(0, 1.0)]),
|
||||
trial_with_values(1, vec![(0, 2.0)]),
|
||||
trial_with_values(2, vec![(0, 3.0)]),
|
||||
trial_with_values(3, vec![(0, 4.0)]),
|
||||
];
|
||||
// 2.6 > 2.5 => prune
|
||||
let current = vec![(0, 2.6)];
|
||||
assert!(pruner.should_prune(4, 0, ¤t, &completed));
|
||||
// 2.4 < 2.5 => don't prune
|
||||
let current = vec![(0, 2.4)];
|
||||
assert!(!pruner.should_prune(4, 0, ¤t, &completed));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn correct_median_with_odd_number_of_trials() {
|
||||
let pruner = MedianPruner::new(Direction::Minimize);
|
||||
// 5 trials at step 0: [1.0, 2.0, 3.0, 4.0, 5.0] => median = 3.0
|
||||
let completed = vec![
|
||||
trial_with_values(0, vec![(0, 1.0)]),
|
||||
trial_with_values(1, vec![(0, 2.0)]),
|
||||
trial_with_values(2, vec![(0, 3.0)]),
|
||||
trial_with_values(3, vec![(0, 4.0)]),
|
||||
trial_with_values(4, vec![(0, 5.0)]),
|
||||
];
|
||||
// 3.5 > 3.0 => prune
|
||||
let current = vec![(0, 3.5)];
|
||||
assert!(pruner.should_prune(5, 0, ¤t, &completed));
|
||||
// 2.5 < 3.0 => don't prune
|
||||
let current = vec![(0, 2.5)];
|
||||
assert!(!pruner.should_prune(5, 0, ¤t, &completed));
|
||||
}
|
||||
|
||||
// --- Non-contiguous step numbers ---
|
||||
|
||||
#[test]
|
||||
fn works_with_non_contiguous_steps() {
|
||||
let pruner = MedianPruner::new(Direction::Minimize);
|
||||
// Steps are 0, 10, 100 — non-contiguous
|
||||
let completed = vec![
|
||||
trial_with_values(0, vec![(0, 1.0), (10, 2.0), (100, 3.0)]),
|
||||
trial_with_values(1, vec![(0, 1.5), (10, 2.5), (100, 4.0)]),
|
||||
trial_with_values(2, vec![(0, 2.0), (10, 3.0), (100, 5.0)]),
|
||||
];
|
||||
// At step 100: [3.0, 4.0, 5.0] => median = 4.0
|
||||
let current = vec![(0, 1.0), (10, 2.0), (100, 4.5)];
|
||||
assert!(pruner.should_prune(3, 100, ¤t, &completed));
|
||||
|
||||
let current = vec![(0, 1.0), (10, 2.0), (100, 3.5)];
|
||||
assert!(!pruner.should_prune(3, 100, ¤t, &completed));
|
||||
}
|
||||
|
||||
// --- No intermediate values for current trial ---
|
||||
|
||||
#[test]
|
||||
fn no_prune_when_no_intermediate_values() {
|
||||
let pruner = MedianPruner::new(Direction::Minimize);
|
||||
let completed = vec![trial_with_values(0, vec![(0, 1.0)])];
|
||||
assert!(!pruner.should_prune(1, 0, &[], &completed));
|
||||
}
|
||||
|
||||
// --- Pruned trials are excluded from median calculation ---
|
||||
|
||||
#[test]
|
||||
fn pruned_trials_excluded_from_median() {
|
||||
use optimizer::TrialState;
|
||||
|
||||
let pruner = MedianPruner::new(Direction::Minimize);
|
||||
|
||||
let mut pruned = trial_with_values(0, vec![(0, 0.1)]);
|
||||
pruned.state = TrialState::Pruned;
|
||||
|
||||
// Only the completed trial (value 5.0) counts. Pruned trial (0.1) is excluded.
|
||||
let completed = vec![pruned, trial_with_values(1, vec![(0, 5.0)])];
|
||||
|
||||
// 3.0 < 5.0 => don't prune (only 1 completed trial with median 5.0)
|
||||
let current = vec![(0, 3.0)];
|
||||
assert!(!pruner.should_prune(2, 0, ¤t, &completed));
|
||||
|
||||
// 6.0 > 5.0 => prune
|
||||
let current = vec![(0, 6.0)];
|
||||
assert!(pruner.should_prune(2, 0, ¤t, &completed));
|
||||
}
|
||||
@@ -0,0 +1,295 @@
|
||||
#![cfg(feature = "serde")]
|
||||
|
||||
use std::collections::HashMap;
|
||||
|
||||
use optimizer::parameter::{FloatParam, IntParam, Parameter};
|
||||
use optimizer::sampler::CompletedTrial;
|
||||
use optimizer::{Direction, ParamValue, Study, StudySnapshot, TrialState};
|
||||
|
||||
#[test]
|
||||
fn round_trip_save_load() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(-10.0, 10.0).name("x");
|
||||
let n = IntParam::new(1, 100).name("n");
|
||||
|
||||
study
|
||||
.optimize(5, |trial| {
|
||||
let x_val = x.suggest(trial)?;
|
||||
let n_val = n.suggest(trial)?;
|
||||
Ok::<_, optimizer::Error>(x_val * x_val + n_val as f64)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let dir = tempdir();
|
||||
let path = dir.join("study.json");
|
||||
|
||||
study.save(&path).unwrap();
|
||||
let loaded: Study<f64> = Study::load(&path).unwrap();
|
||||
|
||||
assert_eq!(loaded.direction(), study.direction());
|
||||
assert_eq!(loaded.n_trials(), study.n_trials());
|
||||
|
||||
let orig_trials = study.trials();
|
||||
let loaded_trials = loaded.trials();
|
||||
|
||||
for (orig, loaded) in orig_trials.iter().zip(loaded_trials.iter()) {
|
||||
assert_eq!(orig.id, loaded.id);
|
||||
assert!((orig.value - loaded.value).abs() < 1e-10);
|
||||
assert_eq!(orig.state, loaded.state);
|
||||
assert_eq!(orig.params.len(), loaded.params.len());
|
||||
assert_eq!(orig.distributions, loaded.distributions);
|
||||
assert_eq!(orig.param_labels, loaded.param_labels);
|
||||
}
|
||||
|
||||
// Clean up
|
||||
std::fs::remove_dir_all(&dir).ok();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn json_output_is_human_readable() {
|
||||
let study: Study<f64> = Study::new(Direction::Maximize);
|
||||
let x = FloatParam::new(0.0, 1.0).name("x");
|
||||
|
||||
study
|
||||
.optimize(2, |trial| {
|
||||
let v = x.suggest(trial)?;
|
||||
Ok::<_, optimizer::Error>(v)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let dir = tempdir();
|
||||
let path = dir.join("study.json");
|
||||
study.save(&path).unwrap();
|
||||
|
||||
let contents = std::fs::read_to_string(&path).unwrap();
|
||||
|
||||
// Verify it's pretty-printed JSON with recognizable fields
|
||||
assert!(contents.contains("\"version\""));
|
||||
assert!(contents.contains("\"direction\""));
|
||||
assert!(contents.contains("\"trials\""));
|
||||
assert!(contents.contains("\"next_trial_id\""));
|
||||
assert!(contents.contains("\"Maximize\""));
|
||||
|
||||
std::fs::remove_dir_all(&dir).ok();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn round_trip_empty_study() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
|
||||
let dir = tempdir();
|
||||
let path = dir.join("empty.json");
|
||||
|
||||
study.save(&path).unwrap();
|
||||
let loaded: Study<f64> = Study::load(&path).unwrap();
|
||||
|
||||
assert_eq!(loaded.direction(), Direction::Minimize);
|
||||
assert_eq!(loaded.n_trials(), 0);
|
||||
|
||||
std::fs::remove_dir_all(&dir).ok();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn snapshot_version_field_is_present() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
|
||||
let dir = tempdir();
|
||||
let path = dir.join("version.json");
|
||||
study.save(&path).unwrap();
|
||||
|
||||
let contents = std::fs::read_to_string(&path).unwrap();
|
||||
let snapshot: StudySnapshot<f64> = serde_json::from_str(&contents).unwrap();
|
||||
|
||||
assert_eq!(snapshot.version, 1);
|
||||
|
||||
std::fs::remove_dir_all(&dir).ok();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn completed_trial_serde_round_trip() {
|
||||
let trial = CompletedTrial::new(42, HashMap::new(), HashMap::new(), HashMap::new(), 2.78);
|
||||
|
||||
let json = serde_json::to_string(&trial).unwrap();
|
||||
let deserialized: CompletedTrial<f64> = serde_json::from_str(&json).unwrap();
|
||||
|
||||
assert_eq!(deserialized.id, 42);
|
||||
assert_eq!(deserialized.value, 2.78);
|
||||
assert_eq!(deserialized.state, TrialState::Complete);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn param_value_serde_round_trip() {
|
||||
let values = vec![
|
||||
ParamValue::Float(1.23),
|
||||
ParamValue::Int(42),
|
||||
ParamValue::Categorical(2),
|
||||
];
|
||||
|
||||
for val in &values {
|
||||
let json = serde_json::to_string(val).unwrap();
|
||||
let deserialized: ParamValue = serde_json::from_str(&json).unwrap();
|
||||
assert_eq!(&deserialized, val);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn direction_serde_round_trip() {
|
||||
let min_json = serde_json::to_string(&Direction::Minimize).unwrap();
|
||||
let max_json = serde_json::to_string(&Direction::Maximize).unwrap();
|
||||
|
||||
assert_eq!(
|
||||
serde_json::from_str::<Direction>(&min_json).unwrap(),
|
||||
Direction::Minimize
|
||||
);
|
||||
assert_eq!(
|
||||
serde_json::from_str::<Direction>(&max_json).unwrap(),
|
||||
Direction::Maximize
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn round_trip_preserves_trial_id_counter() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(0.0, 1.0);
|
||||
|
||||
study
|
||||
.optimize(10, |trial| {
|
||||
let v = x.suggest(trial)?;
|
||||
Ok::<_, optimizer::Error>(v)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let dir = tempdir();
|
||||
let path = dir.join("counter.json");
|
||||
study.save(&path).unwrap();
|
||||
|
||||
let loaded: Study<f64> = Study::load(&path).unwrap();
|
||||
|
||||
// Creating a new trial should use an ID >= 10
|
||||
let trial = loaded.create_trial();
|
||||
assert!(trial.id() >= 10);
|
||||
|
||||
std::fs::remove_dir_all(&dir).ok();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn checkpoint_file_created_at_interval() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(-10.0, 10.0).name("x");
|
||||
|
||||
let dir = tempdir();
|
||||
let checkpoint = dir.join("checkpoint.json");
|
||||
|
||||
study
|
||||
.optimize_with_checkpoint(10, 3, &checkpoint, |trial| {
|
||||
let v = x.suggest(trial)?;
|
||||
Ok::<_, optimizer::Error>(v * v)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
// Checkpoint should exist (written at trials 3, 6, 9)
|
||||
assert!(checkpoint.exists(), "checkpoint file was not created");
|
||||
|
||||
// Load it and verify it's valid
|
||||
let loaded: Study<f64> = Study::load(&checkpoint).unwrap();
|
||||
// Last checkpoint was at trial 9, so it should have 9 trials
|
||||
assert_eq!(loaded.n_trials(), 9);
|
||||
|
||||
std::fs::remove_dir_all(&dir).ok();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn checkpoint_overwrites_previous() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(0.0, 1.0);
|
||||
|
||||
let dir = tempdir();
|
||||
let checkpoint = dir.join("checkpoint.json");
|
||||
|
||||
study
|
||||
.optimize_with_checkpoint(6, 3, &checkpoint, |trial| {
|
||||
let v = x.suggest(trial)?;
|
||||
Ok::<_, optimizer::Error>(v)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
// The checkpoint at trial 6 should overwrite the one from trial 3
|
||||
let loaded: Study<f64> = Study::load(&checkpoint).unwrap();
|
||||
assert_eq!(loaded.n_trials(), 6);
|
||||
|
||||
std::fs::remove_dir_all(&dir).ok();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn resume_from_checkpoint_continues_trial_ids() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(-5.0, 5.0).name("x");
|
||||
|
||||
let dir = tempdir();
|
||||
let checkpoint = dir.join("resume.json");
|
||||
|
||||
// Run 10 trials with checkpointing
|
||||
study
|
||||
.optimize_with_checkpoint(10, 5, &checkpoint, |trial| {
|
||||
let v = x.suggest(trial)?;
|
||||
Ok::<_, optimizer::Error>(v * v)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
// Load and continue
|
||||
let loaded: Study<f64> = Study::load(&checkpoint).unwrap();
|
||||
assert_eq!(loaded.n_trials(), 10);
|
||||
|
||||
let remaining = 15 - loaded.n_trials();
|
||||
loaded
|
||||
.optimize(remaining, |trial| {
|
||||
let v = x.suggest(trial)?;
|
||||
Ok::<_, optimizer::Error>(v * v)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
assert_eq!(loaded.n_trials(), 15);
|
||||
|
||||
// Verify no duplicate trial IDs
|
||||
let trials = loaded.trials();
|
||||
let mut ids: Vec<u64> = trials.iter().map(|t| t.id).collect();
|
||||
ids.sort_unstable();
|
||||
ids.dedup();
|
||||
assert_eq!(ids.len(), 15, "duplicate trial IDs found");
|
||||
|
||||
std::fs::remove_dir_all(&dir).ok();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn atomic_write_no_temp_file_left_behind() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(0.0, 1.0);
|
||||
|
||||
let dir = tempdir();
|
||||
let checkpoint = dir.join("atomic.json");
|
||||
|
||||
study
|
||||
.optimize_with_checkpoint(3, 3, &checkpoint, |trial| {
|
||||
let v = x.suggest(trial)?;
|
||||
Ok::<_, optimizer::Error>(v)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
// The temp file should have been renamed, not left behind
|
||||
let tmp_path = dir.join(".atomic.json.tmp");
|
||||
assert!(!tmp_path.exists(), "temp file was not cleaned up");
|
||||
assert!(checkpoint.exists(), "checkpoint file was not created");
|
||||
|
||||
std::fs::remove_dir_all(&dir).ok();
|
||||
}
|
||||
|
||||
/// Helper to create a unique temporary directory.
|
||||
fn tempdir() -> std::path::PathBuf {
|
||||
use std::sync::atomic::{AtomicU64, Ordering};
|
||||
static COUNTER: AtomicU64 = AtomicU64::new(0);
|
||||
let id = COUNTER.fetch_add(1, Ordering::Relaxed);
|
||||
let dir =
|
||||
std::env::temp_dir().join(format!("optimizer_serde_test_{}_{id}", std::process::id()));
|
||||
std::fs::create_dir_all(&dir).unwrap();
|
||||
dir
|
||||
}
|
||||
@@ -0,0 +1,45 @@
|
||||
#[path = "../benches/test_functions.rs"]
|
||||
mod test_functions;
|
||||
|
||||
use test_functions::*;
|
||||
|
||||
const TOL: f64 = 1e-10;
|
||||
|
||||
#[test]
|
||||
fn sphere_at_optimum() {
|
||||
assert!(sphere(&[0.0, 0.0]).abs() < TOL);
|
||||
assert!(sphere(&[0.0; 10]).abs() < TOL);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rosenbrock_at_optimum() {
|
||||
assert!(rosenbrock(&[1.0, 1.0]).abs() < TOL);
|
||||
assert!(rosenbrock(&[1.0; 5]).abs() < TOL);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rastrigin_at_optimum() {
|
||||
assert!(rastrigin(&[0.0, 0.0]).abs() < TOL);
|
||||
assert!(rastrigin(&[0.0; 10]).abs() < TOL);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn ackley_at_optimum() {
|
||||
assert!(ackley(&[0.0, 0.0]).abs() < 1e-8);
|
||||
assert!(ackley(&[0.0; 10]).abs() < 1e-8);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn branin_at_optimum() {
|
||||
let target = 0.397_887_357_729_738_1;
|
||||
let val = branin(&[std::f64::consts::PI, 2.275]);
|
||||
assert!((val - target).abs() < 1e-3);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn hartmann6_at_optimum() {
|
||||
let target = -3.3224;
|
||||
let x_opt = [0.20169, 0.150011, 0.476874, 0.275332, 0.311652, 0.6573];
|
||||
let val = hartmann6(&x_opt);
|
||||
assert!((val - target).abs() < 0.01);
|
||||
}
|
||||
@@ -0,0 +1,64 @@
|
||||
use optimizer::pruner::{Pruner, ThresholdPruner};
|
||||
|
||||
#[test]
|
||||
fn prune_when_value_exceeds_upper_threshold() {
|
||||
let pruner = ThresholdPruner::new().upper(10.0);
|
||||
let values = vec![(0, 5.0), (1, 8.0), (2, 11.0)];
|
||||
assert!(pruner.should_prune(0, 2, &values, &[]));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn prune_when_value_falls_below_lower_threshold() {
|
||||
let pruner = ThresholdPruner::new().lower(0.0);
|
||||
let values = vec![(0, 5.0), (1, 2.0), (2, -1.0)];
|
||||
assert!(pruner.should_prune(0, 2, &values, &[]));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn no_prune_when_value_within_bounds() {
|
||||
let pruner = ThresholdPruner::new().upper(10.0).lower(0.0);
|
||||
let values = vec![(0, 3.0), (1, 5.0), (2, 7.0)];
|
||||
assert!(!pruner.should_prune(0, 2, &values, &[]));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn no_prune_when_no_intermediate_values() {
|
||||
let pruner = ThresholdPruner::new().upper(10.0).lower(0.0);
|
||||
assert!(!pruner.should_prune(0, 0, &[], &[]));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn works_with_only_upper_set() {
|
||||
let pruner = ThresholdPruner::new().upper(5.0);
|
||||
let below = vec![(0, 3.0)];
|
||||
let above = vec![(0, 6.0)];
|
||||
assert!(!pruner.should_prune(0, 0, &below, &[]));
|
||||
assert!(pruner.should_prune(0, 0, &above, &[]));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn works_with_only_lower_set() {
|
||||
let pruner = ThresholdPruner::new().lower(2.0);
|
||||
let above = vec![(0, 5.0)];
|
||||
let below = vec![(0, 1.0)];
|
||||
assert!(!pruner.should_prune(0, 0, &above, &[]));
|
||||
assert!(pruner.should_prune(0, 0, &below, &[]));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn works_with_both_thresholds_set() {
|
||||
let pruner = ThresholdPruner::new().upper(10.0).lower(0.0);
|
||||
|
||||
// Within bounds
|
||||
assert!(!pruner.should_prune(0, 0, &[(0, 5.0)], &[]));
|
||||
|
||||
// Exceeds upper
|
||||
assert!(pruner.should_prune(0, 0, &[(0, 15.0)], &[]));
|
||||
|
||||
// Below lower
|
||||
assert!(pruner.should_prune(0, 0, &[(0, -3.0)], &[]));
|
||||
|
||||
// At exact boundary (not pruned — strictly greater/less)
|
||||
assert!(!pruner.should_prune(0, 0, &[(0, 10.0)], &[]));
|
||||
assert!(!pruner.should_prune(0, 0, &[(0, 0.0)], &[]));
|
||||
}
|
||||
@@ -0,0 +1,148 @@
|
||||
use optimizer::parameter::{FloatParam, Parameter};
|
||||
use optimizer::{AttrValue, Direction, Study};
|
||||
|
||||
#[test]
|
||||
fn set_and_get_float_attr() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(0.0, 1.0);
|
||||
|
||||
study
|
||||
.optimize(1, |trial| {
|
||||
let _ = x.suggest(trial)?;
|
||||
trial.set_user_attr("score", 42.5);
|
||||
assert_eq!(trial.user_attr("score"), Some(&AttrValue::Float(42.5)));
|
||||
Ok::<_, optimizer::Error>(1.0)
|
||||
})
|
||||
.unwrap();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn set_and_get_int_attr() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(0.0, 1.0);
|
||||
|
||||
study
|
||||
.optimize(1, |trial| {
|
||||
let _ = x.suggest(trial)?;
|
||||
trial.set_user_attr("epoch", 42_i64);
|
||||
assert_eq!(trial.user_attr("epoch"), Some(&AttrValue::Int(42)));
|
||||
Ok::<_, optimizer::Error>(1.0)
|
||||
})
|
||||
.unwrap();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn set_and_get_string_attr() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(0.0, 1.0);
|
||||
|
||||
study
|
||||
.optimize(1, |trial| {
|
||||
let _ = x.suggest(trial)?;
|
||||
trial.set_user_attr("model", "resnet50");
|
||||
assert_eq!(
|
||||
trial.user_attr("model"),
|
||||
Some(&AttrValue::String("resnet50".to_owned()))
|
||||
);
|
||||
Ok::<_, optimizer::Error>(1.0)
|
||||
})
|
||||
.unwrap();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn set_and_get_bool_attr() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(0.0, 1.0);
|
||||
|
||||
study
|
||||
.optimize(1, |trial| {
|
||||
let _ = x.suggest(trial)?;
|
||||
trial.set_user_attr("converged", true);
|
||||
assert_eq!(trial.user_attr("converged"), Some(&AttrValue::Bool(true)));
|
||||
Ok::<_, optimizer::Error>(1.0)
|
||||
})
|
||||
.unwrap();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn attrs_propagate_to_completed_trial() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(0.0, 1.0);
|
||||
|
||||
study
|
||||
.optimize(1, |trial| {
|
||||
let _ = x.suggest(trial)?;
|
||||
trial.set_user_attr("time_secs", 1.5);
|
||||
trial.set_user_attr("tag", "baseline");
|
||||
Ok::<_, optimizer::Error>(1.0)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let best = study.best_trial().unwrap();
|
||||
assert_eq!(best.user_attr("time_secs"), Some(&AttrValue::Float(1.5)));
|
||||
assert_eq!(
|
||||
best.user_attr("tag"),
|
||||
Some(&AttrValue::String("baseline".to_owned()))
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn overwrite_attr_replaces_value() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(0.0, 1.0);
|
||||
|
||||
study
|
||||
.optimize(1, |trial| {
|
||||
let _ = x.suggest(trial)?;
|
||||
trial.set_user_attr("key", "old");
|
||||
trial.set_user_attr("key", "new");
|
||||
assert_eq!(
|
||||
trial.user_attr("key"),
|
||||
Some(&AttrValue::String("new".to_owned()))
|
||||
);
|
||||
Ok::<_, optimizer::Error>(1.0)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let best = study.best_trial().unwrap();
|
||||
assert_eq!(
|
||||
best.user_attr("key"),
|
||||
Some(&AttrValue::String("new".to_owned()))
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn missing_attr_returns_none() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(0.0, 1.0);
|
||||
|
||||
study
|
||||
.optimize(1, |trial| {
|
||||
let _ = x.suggest(trial)?;
|
||||
assert_eq!(trial.user_attr("nonexistent"), None);
|
||||
Ok::<_, optimizer::Error>(1.0)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let best = study.best_trial().unwrap();
|
||||
assert_eq!(best.user_attr("nonexistent"), None);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn user_attrs_map_returns_all() {
|
||||
let study: Study<f64> = Study::new(Direction::Minimize);
|
||||
let x = FloatParam::new(0.0, 1.0);
|
||||
|
||||
study
|
||||
.optimize(1, |trial| {
|
||||
let _ = x.suggest(trial)?;
|
||||
trial.set_user_attr("a", 1.0);
|
||||
trial.set_user_attr("b", true);
|
||||
assert_eq!(trial.user_attrs().len(), 2);
|
||||
Ok::<_, optimizer::Error>(1.0)
|
||||
})
|
||||
.unwrap();
|
||||
|
||||
let best = study.best_trial().unwrap();
|
||||
assert_eq!(best.user_attrs().len(), 2);
|
||||
}
|
||||
Reference in New Issue
Block a user