https://github.com/sile/tpe

A TPE (Tree-structured Parzen Estimator) implementation in Rust
https://github.com/sile/tpe

black-box-optimization hyperparameter-optimization rust tpe

Last synced: about 1 month ago
JSON representation

A TPE (Tree-structured Parzen Estimator) implementation in Rust

• Host: GitHub
• URL: https://github.com/sile/tpe
• Owner: sile
• License: mit
• Created: 2020-09-26T09:39:41.000Z (over 5 years ago)
• Default Branch: main
• Last Pushed: 2026-04-22T10:47:54.000Z (about 1 month ago)
• Last Synced: 2026-04-22T12:31:40.451Z (about 1 month ago)
• Topics: black-box-optimization, hyperparameter-optimization, rust, tpe
• Language: Rust
• Homepage:
• Size: 43 KB
• Stars: 33
• Watchers: 1
• Forks: 8
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
tpe

===

[![tpe](https://img.shields.io/crates/v/tpe.svg)](https://crates.io/crates/tpe)

[![Documentation](https://docs.rs/tpe/badge.svg)](https://docs.rs/tpe)

[![Actions Status](https://github.com/sile/tpe/workflows/CI/badge.svg)](https://github.com/sile/tpe/actions)

[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)

This crate provides a hyperparameter optimization algorithm using TPE (Tree-structured Parzen Estimator).

Examples

--------

### Minimize the result of a quadratic function

An example optimizing a simple quadratic function which has one numerical and one categorical parameter.

```rust

use rand::SeedableRng as _;

let choices = [1, 10, 100];

let mut optim0 =

    tpe::TpeOptimizer::new(tpe::parzen_estimator(), tpe::range(-5.0, 5.0)?);

let mut optim1 =

    tpe::TpeOptimizer::new(tpe::histogram_estimator(), tpe::categorical_range(choices.len())?);

fn objective(x: f64, y: i32) -> f64 {

    x.powi(2) + y as f64

}

let mut best_value = f64::INFINITY;

let mut rng = rand::rngs::StdRng::from_seed(Default::default());

for _ in 0..100 {

   let x = optim0.ask(&mut rng)?;

   let y = optim1.ask(&mut rng)?;

   let v = objective(x, choices[y as usize]);

   optim0.tell(x, v)?;

   optim1.tell(y, v)?;

   best_value = best_value.min(v);

}

assert_eq!(best_value, 1.0001089491396404);

```

References

----------

Please refer to the following papers about the details of TPE:

- [Algorithms for Hyper-Parameter Optimization](https://papers.nips.cc/paper/4443-algorithms-for-hyper-parameter-optimization.pdf)

- [Making a Science of Model Search: Hyperparameter Optimization in Hundreds of Dimensions for Vision Architectures](http://proceedings.mlr.press/v28/bergstra13.pdf)