saealib.PreSelectionStrategy

class saealib.PreSelectionStrategy(n_candidates, n_select)[source]

Bases: OptimizationStrategy

Pre-selection strategy.

Parameters:

  • n_candidates (int)

  • n_select (int)

Methods

__init__

Initialize PreSelectionStrategy.

step

Generate a large candidate pool, screen with surrogate, true-evaluate top-k.

Method Details

PreSelectionStrategy.__init__(n_candidates, n_select)[source]

Initialize PreSelectionStrategy.

Parameters:

  • n_candidates (int) – Number of candidates to generate and score with the surrogate.

  • n_select (int) – Number of top-scoring candidates to evaluate with the true objective function.

PreSelectionStrategy.step(ctx, provider)[source]

Generate a large candidate pool, screen with surrogate, true-evaluate top-k.

Parameters:

  • ctx (OptimizationContext) – Current optimization context.

  • provider (ComponentProvider) – Component provider.

Return type:

None