Standard steepest descent. More...

#include <shark/Algorithms/GradientDescent/SteepestDescent.h>

Inheritance diagram for shark::SteepestDescent:

Public Member Functions
	SteepestDescent ()

std::string	name () const
	From INameable: return the class name. More...

void	init (ObjectiveFunctionType &objectiveFunction, SearchPointType const &startingPoint)
	initializes the optimizer using a predefined starting point More...

double	learningRate () const
	get learning rate More...

void	setLearningRate (double learningRate)
	set learning rate More...

double	momentum () const
	get momentum parameter More...

void	setMomentum (double momentum)
	set momentum parameter More...

void	step (ObjectiveFunctionType const &objectiveFunction)
	updates searchdirection and then does simple gradient descent More...

virtual void	read (InArchive &archive)
	Read the component from the supplied archive. More...

virtual void	write (OutArchive &archive) const
	Write the component to the supplied archive. More...

Public Member Functions inherited from shark::AbstractSingleObjectiveOptimizer< RealVector >
virtual void	init (ObjectiveFunctionType &function)

virtual const SolutionType &	solution () const
	returns the current solution of the optimizer More...

Public Member Functions inherited from shark::AbstractOptimizer< RealVector, double, SingleObjectiveResultSet< RealVector > >
const Features &	features () const

virtual void	updateFeatures ()

bool	requiresValue () const

bool	requiresFirstDerivative () const

bool	requiresSecondDerivative () const

bool	canSolveConstrained () const

bool	requiresClosestFeasible () const

virtual	~AbstractOptimizer ()
	Empty virtual d'tor. More...

Public Member Functions inherited from shark::INameable
virtual	~INameable ()

Public Member Functions inherited from shark::ISerializable
virtual	~ISerializable ()
	Virtual d'tor. More...

void	load (InArchive &archive, unsigned int version)
	Versioned loading of components, calls read(...). More...

void	save (OutArchive &archive, unsigned int version) const
	Versioned storing of components, calls write(...). More...

	BOOST_SERIALIZATION_SPLIT_MEMBER ()

Additional Inherited Members
Public Types inherited from shark::AbstractSingleObjectiveOptimizer< RealVector >
typedef base_type::SearchPointType	SearchPointType

typedef base_type::SolutionType	SolutionType

typedef base_type::ResultType	ResultType

typedef base_type::ObjectiveFunctionType	ObjectiveFunctionType

Public Types inherited from shark::AbstractOptimizer< RealVector, double, SingleObjectiveResultSet< RealVector > >
enum	Feature
	Models features that the optimizer requires from the objective function. More...

typedef RealVector	SearchPointType

typedef double	ResultType

typedef SingleObjectiveResultSet< RealVector >	SolutionType

typedef AbstractObjectiveFunction< RealVector, ResultType >	ObjectiveFunctionType

typedef TypedFlags< Feature >	Features

typedef TypedFeatureNotAvailableException< Feature >	FeatureNotAvailableException

Protected Member Functions inherited from shark::AbstractOptimizer< RealVector, double, SingleObjectiveResultSet< RealVector > >
void	checkFeatures (ObjectiveFunctionType const &objectiveFunction)
	Convenience function that checks whether the features of the supplied objective function match with the required features of the optimizer. More...

Protected Attributes inherited from shark::AbstractSingleObjectiveOptimizer< RealVector >
SolutionType	m_best
	current solution of the optimizer More...

Protected Attributes inherited from shark::AbstractOptimizer< RealVector, double, SingleObjectiveResultSet< RealVector > >
Features	m_features

Detailed Description

Standard steepest descent.

Definition at line 42 of file SteepestDescent.h.

Constructor & Destructor Documentation

§ SteepestDescent()

shark::SteepestDescent::SteepestDescent ( )

inline

Definition at line 45 of file SteepestDescent.h.

References shark::AbstractOptimizer< RealVector, double, SingleObjectiveResultSet< RealVector > >::m_features, and shark::AbstractOptimizer< RealVector, double, SingleObjectiveResultSet< RealVector > >::REQUIRES_FIRST_DERIVATIVE.

Member Function Documentation

§ init()

void shark::SteepestDescent::init	(	ObjectiveFunctionType &	function,
		SearchPointType const &	startingPoint
	)

inlinevirtual

initializes the optimizer using a predefined starting point

Implements shark::AbstractSingleObjectiveOptimizer< RealVector >.

Definition at line 56 of file SteepestDescent.h.

References shark::AbstractOptimizer< RealVector, double, SingleObjectiveResultSet< RealVector > >::checkFeatures(), shark::AbstractObjectiveFunction< PointType, ResultT >::evalDerivative(), shark::AbstractObjectiveFunction< PointType, ResultT >::init(), shark::AbstractSingleObjectiveOptimizer< RealVector >::m_best, shark::ResultSet< SearchPointT, ResultT >::point, and shark::ResultSet< SearchPointT, ResultT >::value.

Referenced by main(), and trainRBM().

§ learningRate()

double shark::SteepestDescent::learningRate ( ) const

inline

get learning rate

Definition at line 70 of file SteepestDescent.h.

Referenced by setLearningRate().

§ momentum()

double shark::SteepestDescent::momentum ( ) const

inline

get momentum parameter

Definition at line 84 of file SteepestDescent.h.

Referenced by setMomentum().

§ name()

std::string shark::SteepestDescent::name ( ) const

inlinevirtual

From INameable: return the class name.

Reimplemented from shark::INameable.

Definition at line 53 of file SteepestDescent.h.

§ read()

virtual void shark::SteepestDescent::read ( InArchive & archive )

inlinevirtual

Read the component from the supplied archive.

Parameters

[in,out] archive The archive to read from.

Reimplemented from shark::ISerializable.

Definition at line 102 of file SteepestDescent.h.

§ setLearningRate()

void shark::SteepestDescent::setLearningRate ( double learningRate )

inline

set learning rate

Definition at line 77 of file SteepestDescent.h.

References learningRate().

Referenced by main(), and trainRBM().

§ setMomentum()

void shark::SteepestDescent::setMomentum ( double momentum )

inline

set momentum parameter

Definition at line 91 of file SteepestDescent.h.

References momentum().

Referenced by main().

§ step()

void shark::SteepestDescent::step ( ObjectiveFunctionType const & objectiveFunction )

inlinevirtual

updates searchdirection and then does simple gradient descent

Implements shark::AbstractOptimizer< RealVector, double, SingleObjectiveResultSet< RealVector > >.

Definition at line 97 of file SteepestDescent.h.

References shark::AbstractObjectiveFunction< PointType, ResultT >::evalDerivative(), shark::AbstractSingleObjectiveOptimizer< RealVector >::m_best, shark::ResultSet< SearchPointT, ResultT >::point, and shark::ResultSet< SearchPointT, ResultT >::value.

Referenced by main(), and trainRBM().

§ write()

virtual void shark::SteepestDescent::write ( OutArchive & archive ) const

inlinevirtual

Write the component to the supplied archive.

Parameters

[in,out] archive The archive to write to.

Reimplemented from shark::ISerializable.

Definition at line 109 of file SteepestDescent.h.

The documentation for this class was generated from the following file:

include/shark/Algorithms/GradientDescent/SteepestDescent.h

Public Member Functions

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

§ SteepestDescent()

Member Function Documentation

§ init()

§ learningRate()

§ momentum()

§ name()

§ read()

§ setLearningRate()

§ setMomentum()

§ step()

§ write()