Crate hyperopt_samplers 

hyperopt-samplers

Pluggable Sampler implementations for hyperopt-rs. All three are interchangeable through the same Study API:

• RandomSampler — independent random draws; the baseline.
• GridSampler — exhaustive enumeration over a caller-provided grid.
• TpeSampler — adaptive Tree-structured Parzen Estimator, wrapping the tpe crate.
• CmaEsSampler — Covariance Matrix Adaptation Evolution Strategy for continuous spaces, implemented from scratch.

Structs

CmaEsSampler

A Sampler driven by CMA-ES over the study’s numeric parameters.

GridSampler

Exhaustive search over a caller-provided discrete grid.

RandomSampler

The simplest possible Sampler: every parameter is drawn independently and uniformly (or log-uniformly / categorically) from its distribution, with no learning from prior trials. It is the right baseline to validate the whole Trial/TrialContext/Study plumbing against, and the reference every adaptive sampler is compared to.

TpeSampler

Tree-structured Parzen Estimator sampler.

Enums

BoundHandling

How CMA-ES repairs a drawn coordinate that lands outside a parameter’s [0, 1] normalized box.