This crate provides a hyperparameter optimization algorithm using TPE (Tree-structured Parzen Estimator).
An example optimizing a simple quadratic function which has one numerical and one categorical parameters. ```rust use rand::SeedableRng as _;
let choices = [1, 10, 100]; let mut optim0 = tpe::TpeOptimizer::new(tpe::parzenestimator(), tpe::range(-5.0, 5.0)?); let mut optim1 = tpe::TpeOptimizer::new(tpe::histogramestimator(), tpe::categorical_range(choices.len())?);
fn objective(x: f64, y: i32) -> f64 { x.powi(2) + y as f64 }
let mut bestvalue = std::f64::INFINITY; let mut rng = rand::rngs::StdRng::fromseed(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)?; bestvalue = bestvalue.min(v); }
asserteq!(bestvalue, 1.000098470725203); ```
kurobako] benchmarkThere is an example examples/tpe-solver.rs which implements
the [kurobako] solver interface, so you can run a benchmark using TPE as follows:
console
$ PROBLEMS=$(kurobako problem-suite sigopt auc)
$ SOLVERS="$(kurobako solver command -- cargo run --release --example tpe-solver) $(kurobako solver optuna)"
$ kurobako studies --solvers $SOLVERS --problems $PROBLEMS --repeats 30 --budget 80 | kurobako run > result.json
$ cat result.json | kurobako report > report.md
Please refer to the following papers about the details of TPE: