Optimize by trying out predefined configurations. More...

#include <shark/Algorithms/DirectSearch/GridSearch.h>

Inheritance diagram for shark::PointSearch:

Public Member Functions
	PointSearch ()
	Constructor. More...

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

void	configure (const std::vector< RealVector > &points)

void	configure (size_t parameters, size_t samples, double min, double max)
	samples random points in the range [min,max]^parameters 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...

void	init (ObjectiveFunctionType &objectiveFunction, SearchPointType const &startingPoint)
	If the class wasn't configured before, this method samples random uniform distributed points in [-1,1]^n. More...

void	step (ObjectiveFunctionType const &objectiveFunction)

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 ()

Protected Attributes
std::vector< RealVector >	m_points
	The array holds one parameter configuration in every column. More...

bool	m_configured
	verbosity level 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

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...

Detailed Description

Optimize by trying out predefined configurations.

: The PointSearch class is similair to the GridSearch class by the property that it optimizes a model in a single pass just trying out a predefined number of parameter configurations. The main difference is that every parameter configuration has to be explicitly defined. It is not possible to define a set of values for every axis; see GridSearch for this purpose. Thus, the PointSearch class allows for more flexibility.

If no configure method is called, this class just samples random points. They are uniformly distributed in [-1,1]. parameters^2 points but minimum 20 are sampled in this case.

Definition at line 567 of file GridSearch.h.

Constructor & Destructor Documentation

§ PointSearch()

shark::PointSearch::PointSearch ( )

inline

Constructor.

Definition at line 571 of file GridSearch.h.

References shark::GridSearch::m_configured.

Member Function Documentation

§ configure() [1/2]

void shark::PointSearch::configure ( const std::vector< RealVector > & points )

inline

Initialization of the search points.

Parameters

points array of points to evaluate

Definition at line 583 of file GridSearch.h.

References shark::GridSearch::m_configured.

§ configure() [2/2]

void shark::PointSearch::configure	(	size_t	parameters,
		size_t	samples,
		double	min,
		double	max
	)

inline

samples random points in the range [min,max]^parameters

Definition at line 589 of file GridSearch.h.

References shark::GridSearch::m_configured, shark::blas::parameters(), RANGE_CHECK, and shark::uni().

§ init()

void shark::PointSearch::init	(	ObjectiveFunctionType &	objectiveFunction,
		SearchPointType const &	startingPoint
	)

inlinevirtual

If the class wasn't configured before, this method samples random uniform distributed points in [-1,1]^n.

Implements shark::AbstractSingleObjectiveOptimizer< RealVector >.

Definition at line 620 of file GridSearch.h.

References shark::AbstractOptimizer< RealVector, double, SingleObjectiveResultSet< RealVector > >::checkFeatures(), shark::GridSearch::configure(), shark::AbstractObjectiveFunction< PointType, ResultT >::init(), shark::GridSearch::m_configured, shark::blas::min(), shark::blas::parameters(), and shark::sqr().

§ name()

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

inlinevirtual

From INameable: return the class name.

Reimplemented from shark::INameable.

Definition at line 576 of file GridSearch.h.

§ read()

virtual void shark::PointSearch::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 603 of file GridSearch.h.

References shark::AbstractSingleObjectiveOptimizer< RealVector >::m_best, shark::GridSearch::m_configured, shark::ResultSet< SearchPointT, ResultT >::point, and shark::ResultSet< SearchPointT, ResultT >::value.

§ step()

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

inlinevirtual

Please note that for the point search optimizer it does not make sense to call step more than once, as the solution does not improve iteratively.

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

Definition at line 635 of file GridSearch.h.

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

§ write()

virtual void shark::PointSearch::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 611 of file GridSearch.h.

References shark::AbstractSingleObjectiveOptimizer< RealVector >::m_best, shark::GridSearch::m_configured, shark::ResultSet< SearchPointT, ResultT >::point, and shark::ResultSet< SearchPointT, ResultT >::value.

Member Data Documentation

§ m_configured

bool shark::PointSearch::m_configured

protected

verbosity level

Definition at line 662 of file GridSearch.h.

§ m_points

std::vector<RealVector> shark::PointSearch::m_points

protected

The array holds one parameter configuration in every column.

Definition at line 659 of file GridSearch.h.

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

include/shark/Algorithms/DirectSearch/GridSearch.h

Public Member Functions

Protected Attributes

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

§ PointSearch()

Member Function Documentation

§ configure() [1/2]

§ configure() [2/2]

§ init()

§ name()

§ read()

§ step()

§ write()

Member Data Documentation

§ m_configured

§ m_points