Conjugate-gradient method for unconstrained optimization. More...

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

Inheritance diagram for shark::CG:

Public Member Functions
std::string	name () const
	returns the name of the object More...

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

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

Public Member Functions inherited from shark::AbstractLineSearchOptimizer
SHARK_EXPORT_SYMBOL	AbstractLineSearchOptimizer ()

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

SHARK_EXPORT_SYMBOL void	step (ObjectiveFunctionType const &objectiveFunction)
	Carry out one step of the optimizer for the supplied objective function. More...

LineSearch const &	lineSearch () const

LineSearch &	lineSearch ()

RealVector const &	derivative () const
	Returns the derivative at the current point. Can be used for stopping criteria. More...

Public Member Functions inherited from shark::AbstractSingleObjectiveOptimizer< RealVector >
std::size_t	numInitPoints () const
	By default most single objective optimizers only require a single point. More...

virtual void	init (ObjectiveFunctionType const &function, std::vector< SearchPointType > const &initPoints)
	Initialize the optimizer for the supplied objective function using a set of initialisation points. More...

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 ()

virtual void	init (ObjectiveFunctionType const &function)
	Initialize the optimizer for the supplied objective function. 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 ()

Protected Member Functions
SHARK_EXPORT_SYMBOL void	initModel ()
	Initializes the internal model. More...

SHARK_EXPORT_SYMBOL void	computeSearchDirection (ObjectiveFunctionType const &objectiveFunction)
	Updates the Model and computes the next search direction. More...

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
unsigned	m_count

Protected Attributes inherited from shark::AbstractLineSearchOptimizer
LineSearch	m_linesearch
	used line search method. More...

std::size_t	m_dimension
	number of parameters More...

double	m_initialStepLength
	Initial step length to begin with the line search. More...

RealVector	m_derivative
	gradient of m_best.point More...

RealVector	m_searchDirection
	search direction of next step More...

RealVector	m_lastPoint
	previous point More...

RealVector	m_lastDerivative
	gradient of the previous point More...

double	m_lastValue
	value of the previous point 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

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

Detailed Description

Conjugate-gradient method for unconstrained optimization.

The next CG search Direction p_{k+1} is computed using the current gradient g_k by \( p_{k+1} = \beta p_k - g_k \) where beta can be computed using different formulas well known is the Fletcher - Reeves method: \( \beta = ||g_k||2/ ||g_{k-1}||^2 \) we use \( \beta = ||g_k||^2 /<p_k,g_k-g_{k-1}> \) which is formula 5.49 in Nocedal, Wright - Numerical Optimization. This formula has better numerical properties than Fletcher-Reeves for non-quadratic functions while ensuring a descent direction.

We implement restarting to ensure quadratic convergence near the optimum as well as numerical stability

Definition at line 58 of file CG.h.

Member Function Documentation

◆ computeSearchDirection()

SHARK_EXPORT_SYMBOL void shark::CG::computeSearchDirection ( ObjectiveFunctionType const & objectiveFunction )

protectedvirtual

Updates the Model and computes the next search direction.

After a step was performed, this method is called to compute the next search direction. This usually involves updating the internal model using the new and old step information. Afterwards m_searchDirection should contain the next search direction.

Implements shark::AbstractLineSearchOptimizer.

◆ initModel()

SHARK_EXPORT_SYMBOL void shark::CG::initModel ( )

protectedvirtual

Initializes the internal model.

Line Search Methods use a Model to search for the next search direction. The model is initialized during init()

Implements shark::AbstractLineSearchOptimizer.

◆ name()

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

inlinevirtual

returns the name of the object

Reimplemented from shark::INameable.

Definition at line 63 of file CG.h.

References read(), SHARK_EXPORT_SYMBOL, and write().

◆ read()

SHARK_EXPORT_SYMBOL void shark::CG::read ( InArchive & archive )

virtual

Read the component from the supplied archive.

Parameters

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

Reimplemented from shark::AbstractLineSearchOptimizer.

Referenced by name().

◆ write()

SHARK_EXPORT_SYMBOL void shark::CG::write ( OutArchive & archive ) const

virtual

Write the component to the supplied archive.

Parameters

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

Reimplemented from shark::AbstractLineSearchOptimizer.

Referenced by name().

Member Data Documentation

◆ m_count

unsigned shark::CG::m_count

protected

Definition at line 70 of file CG.h.

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

include/shark/Algorithms/GradientDescent/CG.h

Public Member Functions

Protected Member Functions

Protected Attributes

Additional Inherited Members