PLearn::GradientOptimizer Class Reference

#include <GradientOptimizer.h>

Inheritance diagram for PLearn::GradientOptimizer:

[legend]Collaboration diagram for PLearn::GradientOptimizer:

[legend]List of all members.


Public Member Functions
	GradientOptimizer (real the_start_learning_rate=0.01, real the_decrease_constant=0, int n_updates=1, const string &filename="", int every_iterations=1)
	GradientOptimizer (VarArray the_params, Var the_cost, real the_start_learning_rate=0.01, real the_decrease_constant=0, int n_updates=1, const string &filename="", int every_iterations=1)
	GradientOptimizer (VarArray the_params, Var the_cost, VarArray update_for_measure, real the_start_learning_rate=0.01, real the_decrease_constant=0, int n_updates=1, const string &filename="", int every_iterations=1)
	PLEARN_DECLARE_OBJECT (GradientOptimizer)
virtual void	makeDeepCopyFromShallowCopy (CopiesMap &copies)
virtual void	build ()
	Should call simply inherited::build(), then this class's build_().
virtual real	optimize ()
	sub-classes should define this, which is the main method
virtual bool	optimizeN (VecStatsCollector &stats_coll)
	sub-classes should define this, which is the new main method
Public Attributes
real	learning_rate
	gradient descent specific parameters (directly modifiable by the user)
real	start_learning_rate
real	decrease_constant
Mat	lr_schedule
Static Protected Member Functions
void	declareOptions (OptionList &ol)
	redefine this in subclasses: call declareOption(...) for each option, and then call inherited::declareOptions(options) ( see the declareOption function further down)
Private Types
typedef Optimizer	inherited
Private Member Functions
void	build_ ()

Member Typedef Documentation

typedef Optimizer PLearn::GradientOptimizer::inherited [private]

Reimplemented from PLearn::Optimizer.
Definition at line 58 of file GradientOptimizer.h.
Referenced by GradientOptimizer().

Constructor & Destructor Documentation

PLearn::GradientOptimizer::GradientOptimizer ( real the_start_learning_rate = 0.01,

real the_decrease_constant = 0,

int n_updates = 1,

const string & filename = "",

int every_iterations = 1

)

Definition at line 52 of file GradientOptimizer.cc.
References inherited.

PLearn::GradientOptimizer::GradientOptimizer ( VarArray the_params,

Var the_cost,

real the_start_learning_rate = 0.01,

real the_decrease_constant = 0,

int n_updates = 1,

const string & filename = "",

int every_iterations = 1

)

Definition at line 60 of file GradientOptimizer.cc.

PLearn::GradientOptimizer::GradientOptimizer ( VarArray the_params,

Var the_cost,

VarArray update_for_measure,

real the_start_learning_rate = 0.01,

real the_decrease_constant = 0,

int n_updates = 1,

const string & filename = "",

int every_iterations = 1

)

Definition at line 69 of file GradientOptimizer.cc.

Member Function Documentation

virtual void PLearn::GradientOptimizer::build ( ) [inline, virtual]

Should call simply inherited::build(), then this class's build_().
This method should be callable again at later times, after modifying some option fields to change the "architecture" of the object.
Reimplemented from PLearn::Optimizer.
Definition at line 100 of file GradientOptimizer.h.
References build_().

void PLearn::GradientOptimizer::build_ ( ) [inline, private]

This method should be redefined in subclasses and do the actual building of the object according to previously set option fields. Constructors can just set option fields, and then call build_. This method is NOT virtual, and will typically be called only from three places: a constructor, the public virtual build() method, and possibly the public virtual read method (which calls its parent's read). build_() can assume that it's parent's build_ has already been called.
Reimplemented from PLearn::Optimizer.
Definition at line 106 of file GradientOptimizer.h.
Referenced by build().

void PLearn::GradientOptimizer::declareOptions ( OptionList & ol ) [static, protected]

redefine this in subclasses: call declareOption(...) for each option, and then call inherited::declareOptions(options) ( see the declareOption function further down)
ex: static void declareOptions(OptionList& ol) { declareOption(ol, "inputsize", &MyObject::inputsize_, OptionBase::buildoption, "the size of the input\n it must be provided"); declareOption(ol, "weights", &MyObject::weights, OptionBase::learntoption, "the learnt model weights"); inherited::declareOptions(ol); }
Reimplemented from PLearn::Optimizer.
Definition at line 81 of file GradientOptimizer.cc.
References PLearn::declareOption(), and PLearn::OptionList.

virtual void PLearn::GradientOptimizer::makeDeepCopyFromShallowCopy ( CopiesMap & copies ) [inline, virtual]

Does the necessary operations to transform a shallow copy (this) into a deep copy by deep-copying all the members that need to be. Typical implementation:
void CLASS_OF_THIS::makeDeepCopyFromShallowCopy(CopiesMap& copies) { SUPERCLASS_OF_THIS::makeDeepCopyFromShallowCopy(copies); member_ptr = member_ptr->deepCopy(copies); member_smartptr = member_smartptr->deepCopy(copies); member_mat.makeDeepCopyFromShallowCopy(copies); member_vec.makeDeepCopyFromShallowCopy(copies); ... }
Reimplemented from PLearn::Object.
Definition at line 98 of file GradientOptimizer.h.
References PLearn::CopiesMap, and makeDeepCopyFromShallowCopy().
Referenced by makeDeepCopyFromShallowCopy().