Training of a regularization network. More...

#include <shark/Algorithms/Trainers/RegularizationNetworkTrainer.h>

Inheritance diagram for shark::RegularizationNetworkTrainer< InputType >:

Public Types
typedef AbstractModel< InputType, RealVector >	ModelType

typedef AbstractKernelFunction< InputType >	KernelType

Public Types inherited from shark::AbstractSvmTrainer< InputType, RealVector, KernelExpansion< InputType > >
typedef AbstractKernelFunction< InputType >	KernelType

Public Types inherited from shark::AbstractTrainer< Model, LabelTypeT >
typedef Model	ModelType

typedef ModelType::InputType	InputType

typedef LabelTypeT	LabelType

typedef LabeledData< InputType, LabelType >	DatasetType

Public Types inherited from shark::IParameterizable<>
typedef RealVector	ParameterVectorType

Public Member Functions
	RegularizationNetworkTrainer (KernelType *kernel, double betaInv, bool unconstrained=false)

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

double	noiseVariance () const
	Returns the assumed noise variance (i.e., 1/C) More...

void	setNoiseVariance (double betaInv)
	Sets the assumed noise variance (i.e., 1/C) More...

double	precision () const
	Returns the precision (i.e., C), the inverse of the assumed noise variance. More...

void	setPrecision (double beta)
	Sets the precision (i.e., C), the inverse of the assumed noise variance. More...

void	train (KernelExpansion< InputType > &svm, const LabeledData< InputType, RealVector > &dataset)

Public Member Functions inherited from shark::AbstractSvmTrainer< InputType, RealVector, KernelExpansion< InputType > >
	AbstractSvmTrainer (KernelType *kernel, double C, bool offset, bool unconstrained=false)

	AbstractSvmTrainer (KernelType *kernel, double negativeC, double positiveC, bool offset, bool unconstrained=false)

double	C () const
	Return the value of the regularization parameter C. More...

void	setC (double C)
	Set the value of the regularization parameter C. More...

RealVector const &	regularizationParameters () const

void	setRegularizationParameters (RealVector const &regularizers)
	Set the value of the regularization parameter C. More...

KernelType *	kernel ()

KernelType const *	kernel () const

void	setKernel (KernelType *kernel)

bool	isUnconstrained () const

bool	trainOffset () const

std::size_t	cacheSize () const

void	setCacheSize (std::size_t size)

RealVector	parameterVector () const
	get the hyper-parameter vector More...

void	setParameterVector (RealVector const &newParameters)
	set the vector of hyper-parameters More...

size_t	numberOfParameters () const
	return the number of hyper-parameters More...

Public Member Functions inherited from shark::AbstractTrainer< Model, LabelTypeT >
virtual void	train (ModelType &model, DatasetType const &dataset)=0
	Core of the Trainer interface. More...

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

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

Public Member Functions inherited from shark::QpConfig
	QpConfig (bool precomputedFlag=false, bool sparsifyFlag=true)
	Constructor. More...

QpStoppingCondition &	stoppingCondition ()
	Read/write access to the stopping condition. More...

QpStoppingCondition const &	stoppingCondition () const
	Read access to the stopping condition. More...

QpSolutionProperties &	solutionProperties ()
	Access to the solution properties. More...

bool &	precomputeKernel ()
	Flag for using a precomputed kernel matrix. More...

bool const &	precomputeKernel () const
	Flag for using a precomputed kernel matrix. More...

bool &	sparsify ()
	Flag for sparsifying the model after training. More...

bool const &	sparsify () const
	Flag for sparsifying the model after training. More...

bool &	shrinking ()
	Flag for shrinking in the decomposition solver. More...

bool const &	shrinking () const
	Flag for shrinking in the decomposition solver. More...

bool &	s2do ()
	Flag for S2DO (instead of SMO) More...

bool const &	s2do () const
	Flag for S2DO (instead of SMO) More...

unsigned int &	verbosity ()
	Verbosity level of the solver. More...

unsigned int const &	verbosity () const
	Verbosity level of the solver. More...

unsigned long long const &	accessCount () const
	Number of kernel accesses. More...

void	setMinAccuracy (double a)

void	setMaxIterations (unsigned long long i)

void	setTargetValue (double v)

void	setMaxSeconds (double s)

Public Member Functions inherited from shark::IParameterizable<>
virtual	~IParameterizable ()

Additional Inherited Members
Protected Attributes inherited from shark::AbstractSvmTrainer< InputType, RealVector, KernelExpansion< InputType > >
KernelType *	m_kernel

RealVector	m_regularizers
	Vector of regularization parameters. More...

bool	m_trainOffset

bool	m_unconstrained
	Is log(C) stored internally as a parameter instead of C? If yes, then we get rid of the constraint C > 0 on the level of the parameter interface. More...

std::size_t	m_cacheSize
	Number of values in the kernel cache. The size of the cache in bytes is the size of one entry (4 for float, 8 for double) times this number. More...

Protected Attributes inherited from shark::QpConfig
QpStoppingCondition	m_stoppingcondition
	conditions for when to stop the QP solver More...

QpSolutionProperties	m_solutionproperties
	properties of the approximate solution found by the solver More...

bool	m_precomputedKernelMatrix
	should the solver use a precomputed kernel matrix? More...

bool	m_sparsify
	should the trainer sparsify the model after training? More...

bool	m_shrinking
	should shrinking be used? More...

bool	m_s2do
	should S2DO be used instead of SMO? More...

unsigned int	m_verbosity
	verbosity level (currently unused) More...

unsigned long long	m_accessCount
	kernel access count More...

Detailed Description

template<class InputType>
class shark::RegularizationNetworkTrainer< InputType >

Training of a regularization network.

A regularization network is a kernel-based model for regression problems. Given are data tuples \( (x_i, y_i) \) with x-component denoting input and y-component denoting a real-valued label (see the tutorial on label conventions; the implementation uses RealVector), a kernel function k(x, x') and a regularization constant \( C > 0\). Let H denote the kernel induced reproducing kernel Hilbert space of k, and let \( \phi \) denote the corresponding feature map. Then the SVM regression function is of the form

\[ f(x) = \langle w, \phi(x) \rangle + b \]

with coefficients w and b given by the (primal) optimization problem

\[ \min \frac{1}{2} \|w\|^2 + C \sum_i L(y_i, f(x_i)), \]

where the simple quadratic loss is employed:

\[ L(y, f(x)) = (y - f(x))^2 \]

Regularization networks can be interpreted as a special type of support vector machine (for regression, with squared loss, and thus with non-sparse weights).

Training a regularization network is identical to training a Gaussian process for regression. The parameter \( C \) then corresponds precision of the noise (denoted by \( \beta \) in Bishop's textbook). The precision is the inverse of the variance of the noise. The variance of the noise is denoted by \( \sigma_n^2 \) in the textbook by Rasmussen and Williams. Accordingly, \( C = 1/\sigma_n^2 \).

Definition at line 86 of file RegularizationNetworkTrainer.h.

Member Typedef Documentation

◆ KernelType

template<class InputType>

typedef AbstractKernelFunction<InputType> shark::RegularizationNetworkTrainer< InputType >::KernelType

Definition at line 90 of file RegularizationNetworkTrainer.h.

◆ ModelType

template<class InputType>

typedef AbstractModel<InputType, RealVector> shark::RegularizationNetworkTrainer< InputType >::ModelType

Definition at line 89 of file RegularizationNetworkTrainer.h.

Constructor & Destructor Documentation

◆ RegularizationNetworkTrainer()

template<class InputType>

shark::RegularizationNetworkTrainer< InputType >::RegularizationNetworkTrainer	(	KernelType *	kernel,
		double	betaInv,
		bool	unconstrained = `false`
	)

inline

Parameters

kernel	Kernel
betaInv	Inverse precision, equal to assumed noise variance, equal to inverse regularization parameter C
unconstrained	Indicates exponential encoding of the regularization parameter

Definition at line 96 of file RegularizationNetworkTrainer.h.

Member Function Documentation

◆ name()

template<class InputType>

std::string shark::RegularizationNetworkTrainer< InputType >::name ( ) const

inlinevirtual

From INameable: return the class name.

Reimplemented from shark::INameable.

Definition at line 101 of file RegularizationNetworkTrainer.h.

◆ noiseVariance()

template<class InputType>

double shark::RegularizationNetworkTrainer< InputType >::noiseVariance ( ) const

inline

Returns the assumed noise variance (i.e., 1/C)

Definition at line 105 of file RegularizationNetworkTrainer.h.

References shark::AbstractSvmTrainer< InputType, RealVector, KernelExpansion< InputType > >::C().

Referenced by shark::RegularizationNetworkTrainer< InputType >::train().

◆ precision()

template<class InputType>

double shark::RegularizationNetworkTrainer< InputType >::precision ( ) const

inline

Returns the precision (i.e., C), the inverse of the assumed noise variance.

Definition at line 112 of file RegularizationNetworkTrainer.h.

References shark::AbstractSvmTrainer< InputType, RealVector, KernelExpansion< InputType > >::C().

◆ setNoiseVariance()

template<class InputType>

void shark::RegularizationNetworkTrainer< InputType >::setNoiseVariance ( double betaInv )

inline

Sets the assumed noise variance (i.e., 1/C)

Definition at line 108 of file RegularizationNetworkTrainer.h.

References shark::AbstractSvmTrainer< InputType, RealVector, KernelExpansion< InputType > >::C().

◆ setPrecision()

template<class InputType>

void shark::RegularizationNetworkTrainer< InputType >::setPrecision ( double beta )

inline

Sets the precision (i.e., C), the inverse of the assumed noise variance.

Definition at line 115 of file RegularizationNetworkTrainer.h.

References beta, and shark::AbstractSvmTrainer< InputType, RealVector, KernelExpansion< InputType > >::C().

◆ train()

template<class InputType>

void shark::RegularizationNetworkTrainer< InputType >::train	(	KernelExpansion< InputType > &	svm,
		const LabeledData< InputType, RealVector > &	dataset
	)

inline

Definition at line 118 of file RegularizationNetworkTrainer.h.

References shark::calculateRegularizedKernelMatrix(), shark::LabeledData< InputT, LabelT >::inputs(), shark::labelDimension(), shark::LabeledData< InputT, LabelT >::labels(), shark::AbstractSvmTrainer< InputType, RealVector, KernelExpansion< InputType > >::m_kernel, shark::mean(), shark::RegularizationNetworkTrainer< InputType >::noiseVariance(), and shark::KernelExpansion< InputType >::setStructure().

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

include/shark/Algorithms/Trainers/RegularizationNetworkTrainer.h

Public Types

Public Member Functions

Additional Inherited Members

Detailed Description

template<class InputType> class shark::RegularizationNetworkTrainer< InputType >

Member Typedef Documentation

◆ KernelType

◆ ModelType

Constructor & Destructor Documentation

◆ RegularizationNetworkTrainer()

Member Function Documentation

◆ name()

◆ noiseVariance()

◆ precision()

◆ setNoiseVariance()

◆ setPrecision()

◆ train()

template<class InputType>
class shark::RegularizationNetworkTrainer< InputType >