org.deeplearning4j.optimize.solvers

Class LBFGS

java.lang.Object

org.deeplearning4j.optimize.solvers.BaseOptimizer

org.deeplearning4j.optimize.solvers.LBFGS

All Implemented Interfaces:

Serializable, ConvexOptimizer

public class LBFGS
extends BaseOptimizer

LBFGS

Author:

Adam Gibson

See Also:

Serialized Form

Field Summary

Fields inherited from class org.deeplearning4j.optimize.solvers.BaseOptimizer

accumulator, computationGraphUpdater, conf, GRADIENT_KEY, lineMaximizer, log, model, oldScore, PARAMS_KEY, score, SCORE_KEY, SEARCH_DIR, searchState, step, stepFunction, stepMax, terminationConditions, trainingListeners, updater

Constructor Summary

Constructors

Constructor and Description
LBFGS(NeuralNetConfiguration conf, StepFunction stepFunction, Collection<TrainingListener> trainingListeners, Collection<TerminationCondition> terminationConditions, Model model)
LBFGS(NeuralNetConfiguration conf, StepFunction stepFunction, Collection<TrainingListener> trainingListeners, Model model)

Method Summary

Modifier and Type	Method and Description
void	postStep(org.nd4j.linalg.api.ndarray.INDArray gradient) Post step to update searchDirection with new gradient and parameter information
void	preProcessLine() Pre preProcess to setup initial searchDirection approximation
void	setupSearchState(org.nd4j.linalg.primitives.Pair<Gradient,Double> pair) Setup the initial search state

Methods inherited from class org.deeplearning4j.optimize.solvers.BaseOptimizer

applyConstraints, batchSize, checkTerminalConditions, getComputationGraphUpdater, getConf, getDefaultStepFunctionForOptimizer, getEpochCount, getGradientsAccumulator, getIterationCount, getUpdater, gradientAndScore, incrementIterationCount, optimize, postFirstStep, score, setBatchSize, setGradientsAccumulator, setListeners, setUpdater, setUpdaterComputationGraph, updateGradientAccordingToParams

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.deeplearning4j.optimize.api.ConvexOptimizer

getStepFunction

Constructor Detail

LBFGS

public LBFGS(NeuralNetConfiguration conf,
             StepFunction stepFunction,
             Collection<TrainingListener> trainingListeners,
             Model model)

LBFGS

public LBFGS(NeuralNetConfiguration conf,
             StepFunction stepFunction,
             Collection<TrainingListener> trainingListeners,
             Collection<TerminationCondition> terminationConditions,
             Model model)

Method Detail

setupSearchState

public void setupSearchState(org.nd4j.linalg.primitives.Pair<Gradient,Double> pair)

Description copied from class: BaseOptimizer

Setup the initial search state

Specified by:

setupSearchState in interface ConvexOptimizer

Overrides:

setupSearchState in class BaseOptimizer

Parameters:

pair - the gradient and score

preProcessLine

public void preProcessLine()

Description copied from class: BaseOptimizer

Pre preProcess to setup initial searchDirection approximation

Specified by:

preProcessLine in interface ConvexOptimizer

Overrides:

preProcessLine in class BaseOptimizer

postStep

public void postStep(org.nd4j.linalg.api.ndarray.INDArray gradient)

Description copied from class: BaseOptimizer

Post step to update searchDirection with new gradient and parameter information

Specified by:

postStep in interface ConvexOptimizer

Overrides:

postStep in class BaseOptimizer