PNormMappingFunction Class Reference

Detailed Description

This implements the P-norm mapping/projection function.

Reference: Gentile, Claudio. "The robustness of the p-norm algorithms." Machine Learning 53.3 (2003): 265-299.

Definition at line 45 of file PNormMappingFunction.h.

Inheritance diagram for PNormMappingFunction:

Public Member Functions
	PNormMappingFunction ()
virtual	~PNormMappingFunction ()
virtual void	set_norm (float64_t p)
virtual SGVector< float64_t >	get_dual_variable (SGVector< float64_t > variable)
virtual void	update_variable (SGVector< float64_t > variable, SGVector< float64_t > dual_variable)
virtual void	update_context (CMinimizerContext *context)
virtual void	load_from_context (CMinimizerContext *context)

Protected Member Functions
virtual void	projection (SGVector< float64_t > input, SGVector< float64_t > output, float64_t degree)

Protected Attributes
float64_t	m_p

Constructor & Destructor Documentation

PNormMappingFunction

(

)

Definition at line 48 of file PNormMappingFunction.h.

virtual ~PNormMappingFunction ( )

virtual

Definition at line 53 of file PNormMappingFunction.h.

Member Function Documentation

virtual SGVector<float64_t> get_dual_variable ( SGVector< float64_t >  variable )

virtual

Get dual variable

Parameters

variable

primal variable

Returns

dual variable

Implements MappingFunction.

Definition at line 74 of file PNormMappingFunction.h.

virtual void load_from_context ( CMinimizerContext *  context )

virtual

Load the given context object to restore mutable variables

This method will be called by SMDMinimizer::load_from_context(CMinimizerContext* context)

Parameters

context

a context object

Implements MappingFunction.

Definition at line 112 of file PNormMappingFunction.h.

virtual void projection ( SGVector< float64_t >  input, SGVector< float64_t >  output, float64_t  degree  )

protectedvirtual

Project the input variable

Parameters

input	input variable
output	store the result
degree	the parameter of the projection

Definition at line 126 of file PNormMappingFunction.h.

virtual void set_norm ( float64_t  p )

virtual

Get the degree of the Norm

Parameters

p	degree of the norm

Definition at line 58 of file PNormMappingFunction.h.

virtual void update_context ( CMinimizerContext *  context )

virtual

Update a context object to store mutable variables used in learning rate

This method will be called by SMDMinimizer::update_context()

Parameters

context

a context object

Implements MappingFunction.

Definition at line 101 of file PNormMappingFunction.h.

virtual void update_variable ( SGVector< float64_t >  variable, SGVector< float64_t >  dual_variable  )

virtual

Update primal variable in place given dual variable

Parameters

variable	primal variable to be updated
dual_variable	dual variable are known

Implements MappingFunction.

Definition at line 88 of file PNormMappingFunction.h.

Member Data Documentation

float64_t m_p

protected

P-norm

Definition at line 118 of file PNormMappingFunction.h.

---

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

• PNormMappingFunction.h