squared loss for regression and classification More...

#include <shark/ObjectiveFunctions/Loss/SquaredLoss.h>

Inheritance diagram for shark::SquaredLoss< OutputType, LabelType >:

Public Types
typedef base_type::BatchOutputType	BatchOutputType

typedef base_type::BatchLabelType	BatchLabelType

Public Types inherited from shark::AbstractLoss< LabelT, OutputT >
typedef OutputT	OutputType

typedef LabelT	LabelType

typedef RealMatrix	MatrixType

typedef Batch< OutputType >::type	BatchOutputType

typedef Batch< LabelType >::type	BatchLabelType

typedef ConstProxyReference< LabelTypeconst >::type	ConstLabelReference
	Const references to LabelType.

typedef ConstProxyReference< OutputTypeconst >::type	ConstOutputReference
	Const references to OutputType.

Public Types inherited from shark::AbstractCost< LabelT, OutputT >
enum	Feature { HAS_FIRST_DERIVATIVE = 1 , HAS_SECOND_DERIVATIVE = 2 , IS_LOSS_FUNCTION = 4 }
	list of features a cost function can have More...

typedef OutputT	OutputType

typedef LabelT	LabelType

typedef Batch< OutputType >::type	BatchOutputType

typedef Batch< LabelType >::type	BatchLabelType

typedef TypedFlags< Feature >	Features

typedef TypedFeatureNotAvailableException< Feature >	FeatureNotAvailableException

Public Member Functions
	SquaredLoss ()
	Constructor.

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

double	eval (BatchLabelType const &labels, BatchOutputType const &predictions) const
	Evaluate the squared loss \( (label - prediction)^2 \).

double	evalDerivative (BatchLabelType const &label, BatchOutputType const &prediction, BatchOutputType &gradient) const

virtual double	eval (BatchLabelType const &target, BatchOutputType const &prediction) const=0
	evaluate the loss for a batch of targets and a prediction

virtual double	eval (ConstLabelReference target, ConstOutputReference prediction) const
	evaluate the loss for a target and a prediction

double	eval (Data< LabelType > const &targets, Data< OutputType > const &predictions) const

Public Member Functions inherited from shark::AbstractLoss< LabelT, OutputT >
	AbstractLoss ()

virtual double	evalDerivative (ConstLabelReference target, ConstOutputReference prediction, OutputType &gradient) const
	evaluate the loss and its derivative for a target and a prediction

virtual double	evalDerivative (ConstLabelReference target, ConstOutputReference prediction, OutputType &gradient, MatrixType &hessian) const
	evaluate the loss and its first and second derivative for a target and a prediction

double	operator() (LabelType const &target, OutputType const &prediction) const
	evaluate the loss for a target and a prediction

double	operator() (BatchLabelType const &target, BatchOutputType const &prediction) const

Public Member Functions inherited from shark::AbstractCost< LabelT, OutputT >
virtual	~AbstractCost ()

const Features &	features () const

virtual void	updateFeatures ()

bool	hasFirstDerivative () const
	returns true when the first parameter derivative is implemented

bool	isLossFunction () const
	returns true when the cost function is in fact a loss function

double	operator() (Data< LabelType > const &targets, Data< OutputType > const &predictions) const

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

Additional Inherited Members
Protected Attributes inherited from shark::AbstractCost< LabelT, OutputT >
Features	m_features

Detailed Description

template<class OutputType = RealVector, class LabelType = OutputType>
class shark::SquaredLoss< OutputType, LabelType >

squared loss for regression and classification

The SquaredLoss computes the squared distance between target and prediction. It is defined for both vectorial as well as integral labels. In the case of integral labels, the label c is interpreted as unit-vector having the c-th component activated.

Definition at line 48 of file SquaredLoss.h.

Member Typedef Documentation

◆ BatchLabelType

template<class OutputType = RealVector, class LabelType = OutputType>

typedef base_type::BatchLabelType shark::SquaredLoss< OutputType, LabelType >::BatchLabelType

Definition at line 53 of file SquaredLoss.h.

◆ BatchOutputType

template<class OutputType = RealVector, class LabelType = OutputType>

typedef base_type::BatchOutputType shark::SquaredLoss< OutputType, LabelType >::BatchOutputType

Definition at line 52 of file SquaredLoss.h.

Constructor & Destructor Documentation

◆ SquaredLoss()

template<class OutputType = RealVector, class LabelType = OutputType>

shark::SquaredLoss< OutputType, LabelType >::SquaredLoss ( )

inline

Constructor.

Definition at line 56 of file SquaredLoss.h.

References shark::AbstractCost< LabelT, OutputT >::HAS_FIRST_DERIVATIVE, and shark::AbstractCost< LabelT, OutputT >::m_features.

Member Function Documentation

◆ eval() [1/4]

template<class OutputType = RealVector, class LabelType = OutputType>

double shark::SquaredLoss< OutputType, LabelType >::eval	(	BatchLabelType const &	labels,
		BatchOutputType const &	predictions
	)		const

inlinevirtual

Evaluate the squared loss \( (label - prediction)^2 \).

Implements shark::AbstractLoss< LabelT, OutputT >.

Definition at line 69 of file SquaredLoss.h.

References SIZE_CHECK, and shark::sqr().

Referenced by shark::SquaredLoss< OutputType, LabelType >::evalDerivative(), shark::SquaredLoss< OutputType, unsigned int >::evalDerivative(), and main().

◆ eval() [2/4]

template<class OutputType = RealVector, class LabelType = OutputType>

virtual double shark::AbstractLoss< LabelT, OutputT >::eval	(	BatchLabelType const &	target,
		BatchOutputType const &	prediction
	)		const

virtual

evaluate the loss for a batch of targets and a prediction

Parameters

target	target values
prediction	predictions, typically made by a model

Implements shark::AbstractLoss< LabelT, OutputT >.

◆ eval() [3/4]

template<class OutputType = RealVector, class LabelType = OutputType>

virtual double shark::AbstractLoss< LabelT, OutputT >::eval	(	ConstLabelReference	target,
		ConstOutputReference	prediction
	)		const

inlinevirtual

evaluate the loss for a target and a prediction

Parameters

target	target value
prediction	prediction, typically made by a model

Reimplemented from shark::AbstractLoss< LabelT, OutputT >.

Definition at line 92 of file AbstractLoss.h.

◆ eval() [4/4]

template<class OutputType = RealVector, class LabelType = OutputType>

double shark::AbstractLoss< LabelT, OutputT >::eval	(	Data< LabelType > const &	targets,
		Data< OutputType > const &	predictions
	)		const

inlinevirtual

from AbstractCost

Parameters

targets	target values
predictions	predictions, typically made by a model

Reimplemented from shark::AbstractLoss< LabelT, OutputT >.

Definition at line 149 of file AbstractLoss.h.

◆ evalDerivative()

template<class OutputType = RealVector, class LabelType = OutputType>

double shark::SquaredLoss< OutputType, LabelType >::evalDerivative	(	BatchLabelType const &	label,
		BatchOutputType const &	prediction,
		BatchOutputType &	gradient
	)		const

inlinevirtual

Evaluate the squared loss \( (label - prediction)^2 \) and its deriative \( \frac{\partial}{\partial prediction} 1/2 (label - prediction)^2 = prediction - label \).

Reimplemented from shark::AbstractLoss< LabelT, OutputT >.

Definition at line 79 of file SquaredLoss.h.

References shark::SquaredLoss< OutputType, LabelType >::eval().

◆ name()

template<class OutputType = RealVector, class LabelType = OutputType>

std::string shark::SquaredLoss< OutputType, LabelType >::name ( ) const

inlinevirtual

From INameable: return the class name.

Reimplemented from shark::INameable.

Definition at line 63 of file SquaredLoss.h.

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

include/shark/ObjectiveFunctions/Loss/SquaredLoss.h

Public Types

Public Member Functions

Additional Inherited Members

Detailed Description

Member Typedef Documentation

◆ BatchLabelType

◆ BatchOutputType

Constructor & Destructor Documentation

◆ SquaredLoss()

Member Function Documentation

◆ eval() [1/4]

◆ eval() [2/4]

◆ eval() [3/4]

◆ eval() [4/4]

◆ evalDerivative()

◆ name()