shark::AbstractStoppingCriterion< ResultSetT > Class Template Reference

Base class for stopping criteria of optimization algorithms. More...

#include <shark/Algorithms/StoppingCriteria/AbstractStoppingCriterion.h>

Inheritance diagram for shark::AbstractStoppingCriterion< ResultSetT >:

Public Types
typedef ResultSetT	ResultSet

Public Member Functions
virtual void	reset ()=0
	resets the internal state. call before a new trial
virtual bool	stop (ResultSet const &set)=0

Detailed Description

template<class ResultSetT>
class shark::AbstractStoppingCriterion< ResultSetT >

Base class for stopping criteria of optimization algorithms.

Each stopping criterion provides a stop method which takes as argument the latest result of an optimization algorithm. This result is passed as a ResultSetT, which is a template type of this interface. In actual implementations, that type will usually hold the latest objective function value reached by the optimizer on the training set, but may also additionally encapsulate a performance value reached on a validation set. The stopping criteria may then use this information to reach their characteristic decision of whether or not stopping the optimization process is indicated or not.

Definition at line 51 of file AbstractStoppingCriterion.h.

Member Typedef Documentation

ResultSet

template<class ResultSetT >

typedef ResultSetT shark::AbstractStoppingCriterion< ResultSetT >::ResultSet

Definition at line 53 of file AbstractStoppingCriterion.h.

Member Function Documentation

reset()

template<class ResultSetT >

virtual void shark::AbstractStoppingCriterion< ResultSetT >::reset ( )

pure virtual

resets the internal state. call before a new trial

Implemented in shark::GeneralizationLoss< PointType >, shark::GeneralizationQuotient< PointType >, shark::MaxIterations< ResultSet >, shark::TrainingError< PointType >, shark::TrainingProgress< PointType >, and shark::ValidatedStoppingCriterion.

Referenced by shark::ValidatedStoppingCriterion::reset(), and shark::OptimizationTrainer< Model, LabelTypeT >::train().

stop()

template<class ResultSetT >

virtual bool shark::AbstractStoppingCriterion< ResultSetT >::stop ( ResultSet const &  set )

pure virtual

after an iteration, updates the internal state and checks whether the algorithm should stop

Parameters

set	the result of the current iteration

Implemented in shark::MaxIterations< ResultSet >, and shark::ValidatedStoppingCriterion.

Referenced by shark::ValidatedStoppingCriterion::stop(), and shark::OptimizationTrainer< Model, LabelTypeT >::train().

---

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

• include/shark/Algorithms/StoppingCriteria/AbstractStoppingCriterion.h