Class EdgeHistogramModel

java.lang.Object

com.knezevic.edaf.v3.models.permutation.EdgeHistogramModel

All Implemented Interfaces:

Model<PermutationVector>

public final class EdgeHistogramModel
extends Object
implements Model<PermutationVector>

Edge Histogram Model (EHM) for permutation EDAs.

Model stores transition probabilities between consecutive items:

   P(next = j | current = i)
 

estimated from elite edge frequencies with additive epsilon smoothing. Sampling builds a Hamiltonian path greedily by repeatedly drawing the next unused item from the transition row of the current item.

Constructor Summary

Constructors

Constructor	Description
EdgeHistogramModel(double epsilon)

Method Summary

Modifier and Type	Method	Description
ModelDiagnostics	diagnostics()	Exposes diagnostics (entropy, covariance condition number, etc.).
void	fit(List<Individual<PermutationVector>> selected, Representation<PermutationVector> representation, RngStream rng)	Fits model parameters from selected individuals.
String	name()	Model identifier used in configuration and listing commands.
void	restore(double[][] transitions)	Restores transition matrix state from checkpoint payload.
List<PermutationVector>	sample(int count, Representation<PermutationVector> representation, Problem<PermutationVector> problem, ConstraintHandling<PermutationVector> constraintHandling, RngStream rng)	Samples new genotypes from model.
double[][]	transitions()	Returns a deep copy of transition matrix for checkpoint persistence.

Methods inherited from class java.lang.Object

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

Methods inherited from interface com.knezevic.edaf.v3.core.api.Model

update

Constructor Details

EdgeHistogramModel

public EdgeHistogramModel(double epsilon)

Parameters:

epsilon - additive smoothing for transition counts

Method Details

name

public String name()

Description copied from interface: Model

Model identifier used in configuration and listing commands.

Specified by:

name in interface Model<PermutationVector>

fit

public void fit(List<Individual<PermutationVector>> selected,
 Representation<PermutationVector> representation,
 RngStream rng)

Description copied from interface: Model

Fits model parameters from selected individuals.

Specified by:

fit in interface Model<PermutationVector>

sample

public List<PermutationVector> sample(int count,
 Representation<PermutationVector> representation,
 Problem<PermutationVector> problem,
 ConstraintHandling<PermutationVector> constraintHandling,
 RngStream rng)

Description copied from interface: Model

Samples new genotypes from model.

Specified by:

sample in interface Model<PermutationVector>

diagnostics

public ModelDiagnostics diagnostics()

Description copied from interface: Model

Exposes diagnostics (entropy, covariance condition number, etc.).

Specified by:

diagnostics in interface Model<PermutationVector>

transitions

public double[][] transitions()

Returns a deep copy of transition matrix for checkpoint persistence.

restore

public void restore(double[][] transitions)

Restores transition matrix state from checkpoint payload.