io.improbable.keanu.algorithms.variational.optimizer

Interface Optimizer

All Known Implementing Classes:

GradientOptimizer, NonGradientOptimizer

public interface Optimizer

Method Summary

Modifier and Type	Method and Description
void	addFitnessCalculationHandler(java.util.function.BiConsumer<java.util.Map<VariableReference,DoubleTensor>,java.lang.Double> fitnessCalculationHandler) Adds a callback to be called whenever the optimizer evaluates the fitness of a point.
static java.util.Map<VariableReference,DoubleTensor>	convertFromPoint(double[] point, java.util.List<? extends Variable> latentVariables)
static double[]	convertToArrayPoint(java.util.List<? extends Variable<? extends NumberTensor,?>> latentVariables)
static java.util.Map<VariableReference,DoubleTensor>	convertToMapPoint(java.util.List<? extends Variable> variables)
static StatusBar	createFitnessStatusBar(Optimizer optimizerThatNeedsStatusBar)
static java.util.List<Variable<? extends DoubleTensor,?>>	getAsDoubleTensors(java.util.List<? extends Variable> variables)
OptimizedResult	maxAPosteriori() This will use MAP estimation to optimize the values of latent vertices such that the probability of the whole Bayesian network is maximised.
OptimizedResult	maxLikelihood() This method will use Maximum Likelihood estimation to optimize the values of latent vertices such that the probability of the observed vertices is maximised.
static long	numDimensions(long[] shape)
void	removeFitnessCalculationHandler(java.util.function.BiConsumer<java.util.Map<VariableReference,DoubleTensor>,java.lang.Double> fitnessCalculationHandler) Removes a callback function that previously would have been called whenever the optimizer evaluated the fitness of a point.
static Variable<DoubleTensor,?>	toDoubleTensorVariable(Variable<?,?> v)
static long	totalNumberOfLatentDimensions(java.util.List<long[]> continuousLatentVariableShapes)

Method Detail

addFitnessCalculationHandler

void addFitnessCalculationHandler(java.util.function.BiConsumer<java.util.Map<VariableReference,DoubleTensor>,java.lang.Double> fitnessCalculationHandler)

Adds a callback to be called whenever the optimizer evaluates the fitness of a point. E.g. for logging.

Parameters:

fitnessCalculationHandler - a function to be called whenever the optimizer evaluates the fitness of a point. The first argument to the handler represents the point being evaluated. The second argument to the handler represents the fitness of that point.

removeFitnessCalculationHandler

void removeFitnessCalculationHandler(java.util.function.BiConsumer<java.util.Map<VariableReference,DoubleTensor>,java.lang.Double> fitnessCalculationHandler)

Removes a callback function that previously would have been called whenever the optimizer evaluated the fitness of a point. If the callback is not registered then this function will do nothing.

Parameters:

fitnessCalculationHandler - the function to be removed from the list of fitness evaluation callbacks

maxAPosteriori

OptimizedResult maxAPosteriori()

This will use MAP estimation to optimize the values of latent vertices such that the probability of the whole Bayesian network is maximised. This method will modify in place the Bayesian network that was used to create this object.

Returns:

the natural logarithm of the Maximum a posteriori (MAP)

maxLikelihood

OptimizedResult maxLikelihood()

This method will use Maximum Likelihood estimation to optimize the values of latent vertices such that the probability of the observed vertices is maximised. This method will modify in place the Bayesian network that was used to create this object.

Returns:

the natural logarithm of the maximum likelihood (MLE)

convertToArrayPoint

static double[] convertToArrayPoint(java.util.List<? extends Variable<? extends NumberTensor,?>> latentVariables)

convertToMapPoint

static java.util.Map<VariableReference,DoubleTensor> convertToMapPoint(java.util.List<? extends Variable> variables)

convertFromPoint

static java.util.Map<VariableReference,DoubleTensor> convertFromPoint(double[] point,
                                                                      java.util.List<? extends Variable> latentVariables)

totalNumberOfLatentDimensions

static long totalNumberOfLatentDimensions(java.util.List<long[]> continuousLatentVariableShapes)

numDimensions

static long numDimensions(long[] shape)

getAsDoubleTensors

static java.util.List<Variable<? extends DoubleTensor,?>> getAsDoubleTensors(java.util.List<? extends Variable> variables)

toDoubleTensorVariable

static Variable<DoubleTensor,?> toDoubleTensorVariable(Variable<?,?> v)

createFitnessStatusBar

static StatusBar createFitnessStatusBar(Optimizer optimizerThatNeedsStatusBar)