Class NoisyResamplingEdaAlgorithm<G>

java.lang.Object

com.knezevic.edaf.v3.core.api.AbstractEdaAlgorithm<G>

com.knezevic.edaf.v3.algorithms.dynamic.AdaptiveRatioEdaAlgorithm<G>

com.knezevic.edaf.v3.algorithms.dynamic.NoisyResamplingEdaAlgorithm<G>

All Implemented Interfaces:

Algorithm<G>

public final class NoisyResamplingEdaAlgorithm<G>
extends AdaptiveRatioEdaAlgorithm<G>

Noisy-optimization EDA driver with per-candidate fitness resampling.

Constructor Summary

Constructors

Constructor	Description
NoisyResamplingEdaAlgorithm(double selectionRatio, double minRatio, double maxRatio, int resamples, double noiseThreshold, double adjustmentStep)

Method Summary

Modifier and Type	Method	Description
protected void	adaptRatio(double normalizedImprovement)
protected Fitness	evaluateGenotype(AlgorithmContext<G> context, G feasibleGenotype, RngStream evaluationRng)	Evaluates one feasible genotype.

Methods inherited from class com.knezevic.edaf.v3.algorithms.dynamic.AdaptiveRatioEdaAlgorithm

afterIteration, clamp, id, ratio, selectionSize, setRatio

Methods inherited from class com.knezevic.edaf.v3.core.api.AbstractEdaAlgorithm

complete, initialize, iterate, postProcessPopulation, restoreState, result, run, state

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

NoisyResamplingEdaAlgorithm

public NoisyResamplingEdaAlgorithm(double selectionRatio,
 double minRatio,
 double maxRatio,
 int resamples,
 double noiseThreshold,
 double adjustmentStep)

Method Details

evaluateGenotype

protected Fitness evaluateGenotype(AlgorithmContext<G> context,
 G feasibleGenotype,
 RngStream evaluationRng)

Description copied from class: AbstractEdaAlgorithm

Evaluates one feasible genotype.

Specialized algorithms can override this hook for noisy resampling or surrogate-assisted evaluation while preserving the shared iteration flow.

Overrides:

evaluateGenotype in class AbstractEdaAlgorithm<G>

adaptRatio

protected void adaptRatio(double normalizedImprovement)

Specified by:

adaptRatio in class AdaptiveRatioEdaAlgorithm<G>