io.improbable.keanu.algorithms.variational

Class NonGradientOptimizer

java.lang.Object

io.improbable.keanu.algorithms.variational.Optimizer

io.improbable.keanu.algorithms.variational.NonGradientOptimizer

public class NonGradientOptimizer
extends Optimizer

Constructor Summary

Constructors

Constructor and Description
NonGradientOptimizer(BayesianNetwork bayesNet)
NonGradientOptimizer(java.util.List<Vertex<java.lang.Double>> graph)

Method Summary

Modifier and Type	Method and Description
double	maxAPosteriori(int maxEvaluations, double boundsRange)
double	maxLikelihood(int maxEvaluations, double boundsRange)
void	onFitnessCalculation(java.util.function.BiConsumer<double[],java.lang.Double> fitnessCalculationHandler)
double	optimize(int maxEvaluations, double boundsRange, java.util.List<Vertex> outputVertices)

Methods inherited from class io.improbable.keanu.algorithms.variational.Optimizer

currentPoint, totalNumLatentDimensions

Methods inherited from class java.lang.Object

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

Constructor Detail

NonGradientOptimizer

public NonGradientOptimizer(BayesianNetwork bayesNet)

NonGradientOptimizer

public NonGradientOptimizer(java.util.List<Vertex<java.lang.Double>> graph)

Method Detail

onFitnessCalculation

public void onFitnessCalculation(java.util.function.BiConsumer<double[],java.lang.Double> fitnessCalculationHandler)

optimize

public double optimize(int maxEvaluations,
                       double boundsRange,
                       java.util.List<Vertex> outputVertices)

maxAPosteriori

public double maxAPosteriori(int maxEvaluations,
                             double boundsRange)

Parameters:

maxEvaluations - throws an exception if the optimizer doesn't converge within this many evaluations

boundsRange - bounding box around starting point

Returns:

the natural logarithm of the Maximum a posteriori (MAP)

maxLikelihood

public double maxLikelihood(int maxEvaluations,
                            double boundsRange)

Parameters:

maxEvaluations - throws an exception if the optimizer doesn't converge within this many evaluations

boundsRange - bounding box around starting point

Returns:

the natural logarithm of the maximum likelihood