metaheuristic_designer.strategies.bayesian_optimization package

Submodules

metaheuristic_designer.strategies.bayesian_optimization.bayesian_optimization module

Bayesian Optimization strategy.

class BayesianOptimization(initializer: Initializer, parent_sel: ParentSelection | None = None, name: str = 'Bayesian Optimization', **kwargs)

Bases: SearchStrategy

Bayesian Optimization using a Gaussian Process surrogate.

This strategy replaces the usual perturbation operator with a BOOperator, which fits a GP model to the current population and uses an acquisition function to propose new candidates.

Parameters:

• initializer (Initializer) – Population initializer (provides the starting points).

• parent_sel (ParentSelection, optional) – Parent selection method (default: identity).

• name (str, optional) – Display name (default "Bayesian Optimization").

• **kwargs – Forwarded to BOOperator (e.g., batch_size, max_samples, kernel).

Module contents

Bayesian optimization strategy.

class BayesianOptimization(initializer: Initializer, parent_sel: ParentSelection | None = None, name: str = 'Bayesian Optimization', **kwargs)

Bases: SearchStrategy

Bayesian Optimization using a Gaussian Process surrogate.

This strategy replaces the usual perturbation operator with a BOOperator, which fits a GP model to the current population and uses an acquisition function to propose new candidates.

Parameters:

• initializer (Initializer) – Population initializer (provides the starting points).

• parent_sel (ParentSelection, optional) – Parent selection method (default: identity).

• name (str, optional) – Display name (default "Bayesian Optimization").

• **kwargs – Forwarded to BOOperator (e.g., batch_size, max_samples, kernel).