cotengra.hyperoptimizers.hyper_cmaes

Hyper parameter optimization using cmaes, as implemented by

https://github.com/CyberAgentAILab/cmaes.

Classes

HyperCMAESSampler
CMAESOptLib	Hyper-optimization using CMA-ES with per-method optimizers and

Module Contents

class cotengra.hyperoptimizers.hyper_cmaes.HyperCMAESSampler(space, sigma=1.0, lr_adapt=True, separable=False, exponential_param_power=None, **kwargs)

params = []

opt

_trial_counter = 0

_trial_store

_batch = []

ask()

tell(trial_number, value)

class cotengra.hyperoptimizers.hyper_cmaes.CMAESOptLib

Bases: cotengra.hyperoptimizers.hyper.HyperOptLib

Hyper-optimization using CMA-ES with per-method optimizers and a Lower Confidence Bound method selector.

setup(methods, space, optimizer=None, sigma=1.0, lr_adapt=True, method_exploration=1.0, method_temperature=1.0, exponential_param_power=None, **cmaes_opts)

Initialize the optimizer state.

Parameters:

• methods (list[str]) – The list of contraction methods to optimize over.

• space (dict[str, dict[str, dict]]) – The search space for each method.

• optimizer (HyperOptimizer, optional) – The parent HyperOptimizer instance, for accessing attributes like max_repeats.

• kwargs – Extra options specific to the optimizer library.

get_setting()

Suggest the next setting to trial.

Returns:

setting – Must contain at least {"method": str, "params": dict}. May also include tokens for reporting.

Return type:

dict

report_result(setting, trial, score)

Report the result of a trial.

Parameters:

• setting (dict) – The setting dict returned by get_setting.

• trial (dict) – The trial result dict.

• score (float) – The scalar score for this trial.