cotengra.hyperoptimizers.hyper_nevergrad

Hyper optimization using nevergrad.

Module Contents

Functions

convert_param_to_nevergrad(param)

get_methods_space(methods)

convert_to_nevergrad_space(method, space)

nevergrad_init_optimizers(self, methods, space[, ...])

Initialize the nevergrad optimizer.

nevergrad_get_setting(self)

Get a setting to trial from one of the nevergrad optimizers.

nevergrad_report_result(self, setting, trial, score)

Report the result of a trial to the nevergrad optimizers.
cotengra.hyperoptimizers.hyper_nevergrad.convert_param_to_nevergrad(param)[source]
cotengra.hyperoptimizers.hyper_nevergrad.get_methods_space(methods)[source]
cotengra.hyperoptimizers.hyper_nevergrad.convert_to_nevergrad_space(method, space)[source]
cotengra.hyperoptimizers.hyper_nevergrad.nevergrad_init_optimizers(self, methods, space, sampler='NaiveTBPSA', method_sampler=None, budget='auto', num_workers=1, method_budget='auto', method_num_workers=1, sampler_opts=None, method_sampler_opts=None)[source]

Initialize the nevergrad optimizer.

Parameters:

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

  • sampler (str, optional) – The optimizer to use to search each method’s search space, see https://facebookresearch.github.io/nevergrad/optimizers_ref.html.

  • method_sampler – The meta-optimizer to use to select overall methods.

  • str – The meta-optimizer to use to select overall methods.

  • optional – The meta-optimizer to use to select overall methods.

  • budget (int, optional) – Supplied to optimizer.

  • num_workers (int, optional) – Supplied to optimizer.

  • method_budget (int, optional) – Supplied to meta-optimizer.

  • method_num_workers (int, optional) – Supplied to meta-optimizer.

cotengra.hyperoptimizers.hyper_nevergrad.nevergrad_get_setting(self)[source]

Get a setting to trial from one of the nevergrad optimizers.

cotengra.hyperoptimizers.hyper_nevergrad.nevergrad_report_result(self, setting, trial, score)[source]

Report the result of a trial to the nevergrad optimizers.