itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType > Class Template Reference

#include <itkQuasiNewtonOptimizerv4.h>

Inheritance diagram for itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >:

Collaboration diagram for itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >:

Detailed Description

template<typename TInternalComputationValueType>
class itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >

Implement a Quasi-Newton optimizer with BFGS Hessian estimation.

Second order approximation of the cost function is usually more efficient since it estimates the descent or ascent direction more precisely. However, computation of Hessian is usually expensive or unavailable. Alternatively Quasi-Newton methods can estimate a Hessian from the gradients in previous steps. Here a specific Quasi-Newton method, BFGS, is used to compute the Quasi-Newton steps.

The Quasi-Newton method doesn't produce a valid step sometimes, ex. when the metric function is not a convex locally. In this scenario, the gradient step is used after being scaled properly.

A helper member object, m_ScalesEstimator may be set to estimate parameter scales and step scales. A step scale measures the magnitude of a step and is used for learning rate computation.

When m_ScalesEstimator is set, SetMaximumNewtonStepSizeInPhysicalUnits() may be called to set the maximum step size. If it is not called, m_MaximumNewtonStepSizeInPhysicalUnits defaults to lambda * OptimizerParameterScalesEstimatorTemplate::EstimateMaximumStepSize(), where lambda is in [1,5].

When m_ScalesEstimator is not set, the parameter scales and learning rates defaults to ones, or can be set by users manually.

Definition at line 59 of file itkQuasiNewtonOptimizerv4.h.

Public Types
typedef SmartPointer< const Self >	ConstPointer
typedef Superclass::DerivativeType	DerivativeType
typedef std::vector< HessianType >	HessianArrayType
typedef itk::Array2D < TInternalComputationValueType >	HessianType
typedef Superclass::IndexRangeType	IndexRangeType
typedef TInternalComputationValueType	InternalComputationValueType
typedef Superclass::MeasureType	MeasureType
typedef Superclass::ParametersType	ParametersType
typedef SmartPointer< Self >	Pointer
typedef QuasiNewtonOptimizerv4Template	Self
typedef Superclass::StopConditionType	StopConditionType
typedef GradientDescentOptimizerv4Template < TInternalComputationValueType >	Superclass
Public Types inherited from itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >
typedef SmartPointer< const Self >	ConstPointer
typedef Superclass::DerivativeType	DerivativeType
typedef Superclass::IndexRangeType	IndexRangeType
typedef TInternalComputationValueType	InternalComputationValueType
typedef Superclass::MeasureType	MeasureType
typedef Superclass::ParametersType	ParametersType
typedef SmartPointer< Self >	Pointer
typedef Superclass::ScalesType	ScalesType
typedef GradientDescentOptimizerv4Template	Self
typedef Superclass::StopConditionType	StopConditionType
typedef GradientDescentOptimizerBasev4Template < TInternalComputationValueType >	Superclass
Public Types inherited from itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >
typedef SmartPointer< const Self >	ConstPointer
typedef itk::Function::WindowConvergenceMonitoringFunction < TInternalComputationValueType >	ConvergenceMonitoringType
typedef Superclass::DerivativeType	DerivativeType
typedef ThreadedIndexedContainerPartitioner::IndexRangeType	IndexRangeType
typedef TInternalComputationValueType	InternalComputationValueType
typedef Superclass::MeasureType	MeasureType
typedef Superclass::MetricType	MetricType
typedef MetricType::Pointer	MetricTypePointer
typedef Superclass::ParametersType	ParametersType
typedef SmartPointer< Self >	Pointer
typedef Superclass::ScalesType	ScalesType
typedef GradientDescentOptimizerBasev4Template	Self
typedef Superclass::StopConditionDescriptionType	StopConditionDescriptionType
typedef Superclass::StopConditionReturnStringType	StopConditionReturnStringType
enum	StopConditionType {   MAXIMUM_NUMBER_OF_ITERATIONS,   COSTFUNCTION_ERROR,   UPDATE_PARAMETERS_ERROR,   STEP_TOO_SMALL,   CONVERGENCE_CHECKER_PASSED,   GRADIENT_MAGNITUDE_TOLEARANCE,   OTHER_ERROR }
typedef ObjectToObjectOptimizerBaseTemplate < TInternalComputationValueType >	Superclass
Public Types inherited from itk::ObjectToObjectOptimizerBaseTemplate< TInternalComputationValueType >
typedef SmartPointer< const Self >	ConstPointer
typedef MetricType::DerivativeType	DerivativeType
typedef MetricType::MeasureType	MeasureType
typedef ObjectToObjectMetricBaseTemplate < TInternalComputationValueType >	MetricType
typedef MetricType::Pointer	MetricTypePointer
typedef MetricType::NumberOfParametersType	NumberOfParametersType
typedef OptimizerParameters < TInternalComputationValueType >	ParametersType
typedef SmartPointer< Self >	Pointer
typedef OptimizerParameterScalesEstimatorTemplate < TInternalComputationValueType >	ScalesEstimatorType
typedef OptimizerParameters < TInternalComputationValueType >	ScalesType
typedef ObjectToObjectOptimizerBaseTemplate	Self
typedef std::ostringstream	StopConditionDescriptionType
typedef std::string	StopConditionReturnStringType
typedef Object	Superclass
Public Types inherited from itk::Object
typedef SmartPointer< const Self >	ConstPointer
typedef SmartPointer< Self >	Pointer
typedef Object	Self
typedef LightObject	Superclass
Public Types inherited from itk::LightObject
typedef SmartPointer< const Self >	ConstPointer
typedef SmartPointer< Self >	Pointer
typedef LightObject	Self

Public Member Functions
virtual ::itk::LightObject::Pointer	CreateAnother (void) const
virtual void	EstimateNewtonStepOverSubRange (const IndexRangeType &subrange)
virtual const char *	GetNameOfClass () const
virtual const DerivativeType &	GetNewtonStep () const
virtual void	SetMaximumIterationsWithoutProgress (SizeValueType _arg)
virtual void	SetMaximumNewtonStepSizeInPhysicalUnits (TInternalComputationValueType _arg)
virtual void	StartOptimization (bool doOnlyInitialization=false)
Public Member Functions inherited from itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >
virtual void	EstimateLearningRate ()
virtual const TInternalComputationValueType &	GetConvergenceValue () const
virtual const TInternalComputationValueType &	GetLearningRate () const
virtual const TInternalComputationValueType &	GetMaximumStepSizeInPhysicalUnits () const
virtual void	ResumeOptimization () ITK_OVERRIDE
virtual void	SetConvergenceWindowSize (SizeValueType _arg)
virtual void	SetLearningRate (TInternalComputationValueType _arg)
virtual void	SetMaximumStepSizeInPhysicalUnits (TInternalComputationValueType _arg)
virtual void	SetMinimumConvergenceValue (TInternalComputationValueType _arg)
virtual void	StopOptimization (void) ITK_OVERRIDE
virtual void	SetDoEstimateLearningRateAtEachIteration (bool _arg)
virtual const bool &	GetDoEstimateLearningRateAtEachIteration () const
virtual void	DoEstimateLearningRateAtEachIterationOn ()
virtual void	DoEstimateLearningRateAtEachIterationOff ()
virtual void	SetDoEstimateLearningRateOnce (bool _arg)
virtual const bool &	GetDoEstimateLearningRateOnce () const
virtual void	DoEstimateLearningRateOnceOn ()
virtual void	DoEstimateLearningRateOnceOff ()
virtual void	SetReturnBestParametersAndValue (bool _arg)
virtual const bool &	GetReturnBestParametersAndValue () const
virtual void	ReturnBestParametersAndValueOn ()
virtual void	ReturnBestParametersAndValueOff ()
Public Member Functions inherited from itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >
virtual SizeValueType	GetCurrentIteration () const
virtual const DerivativeType &	GetGradient () const
virtual SizeValueType	GetNumberOfIterations () const
virtual const StopConditionType &	GetStopCondition () const
virtual const StopConditionReturnStringType	GetStopConditionDescription () const ITK_OVERRIDE
virtual void	SetNumberOfIterations (SizeValueType _arg)
virtual void	ModifyGradientByScales ()
virtual void	ModifyGradientByLearningRate ()
Public Member Functions inherited from itk::ObjectToObjectOptimizerBaseTemplate< TInternalComputationValueType >
virtual const MeasureType &	GetCurrentMetricValue () const
virtual const ParametersType &	GetCurrentPosition () const
virtual const ThreadIdType &	GetNumberOfThreads () const
virtual const ScalesType &	GetScales () const
virtual const bool &	GetScalesAreIdentity () const
bool	GetScalesInitialized (void) const
virtual const MeasureType &	GetValue () const
virtual const ScalesType &	GetWeights () const
virtual const bool &	GetWeightsAreIdentity () const
virtual void	SetNumberOfThreads (ThreadIdType number)
virtual void	SetScalesEstimator (ScalesEstimatorType *_arg)
virtual void	SetWeights (ScalesType _arg)
virtual void	SetMetric (MetricType *_arg)
virtual MetricType *	GetModifiableMetric ()
virtual const MetricType *	GetMetric () const
virtual void	SetScales (const ScalesType &scales)
virtual void	SetDoEstimateScales (bool _arg)
virtual const bool &	GetDoEstimateScales () const
virtual void	DoEstimateScalesOn ()
virtual void	DoEstimateScalesOff ()
Public Member Functions inherited from itk::Object
unsigned long	AddObserver (const EventObject &event, Command *)
unsigned long	AddObserver (const EventObject &event, Command *) const
virtual void	DebugOff () const
virtual void	DebugOn () const
Command *	GetCommand (unsigned long tag)
bool	GetDebug () const
MetaDataDictionary &	GetMetaDataDictionary (void)
const MetaDataDictionary &	GetMetaDataDictionary (void) const
virtual ModifiedTimeType	GetMTime () const
virtual const TimeStamp &	GetTimeStamp () const
bool	HasObserver (const EventObject &event) const
void	InvokeEvent (const EventObject &)
void	InvokeEvent (const EventObject &) const
virtual void	Modified () const
virtual void	Register () const ITK_OVERRIDE
void	RemoveAllObservers ()
void	RemoveObserver (unsigned long tag)
void	SetDebug (bool debugFlag) const
void	SetMetaDataDictionary (const MetaDataDictionary &rhs)
virtual void	SetReferenceCount (int) ITK_OVERRIDE
virtual void	UnRegister () const ITK_OVERRIDE
virtual void	SetObjectName (std::string _arg)
virtual const std::string &	GetObjectName () const
Public Member Functions inherited from itk::LightObject
virtual void	Delete ()
virtual int	GetReferenceCount () const
	itkCloneMacro (Self)
void	Print (std::ostream &os, Indent indent=0) const

Static Public Member Functions
static Pointer	New ()
Static Public Member Functions inherited from itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >
static Pointer	New ()
Static Public Member Functions inherited from itk::Object
static bool	GetGlobalWarningDisplay ()
static void	GlobalWarningDisplayOff ()
static void	GlobalWarningDisplayOn ()
static Pointer	New ()
static void	SetGlobalWarningDisplay (bool flag)
Static Public Member Functions inherited from itk::LightObject
static void	BreakOnError ()
static Pointer	New ()

Protected Member Functions
virtual void	AdvanceOneStep (void)
void	CombineGradientNewtonStep (void)
virtual bool	ComputeHessianAndStepWithBFGS (IndexValueType location)
virtual void	EstimateNewtonStep ()
void	ModifyCombinedNewtonStep ()
virtual void	PrintSelf (std::ostream &os, Indent indent) const
	QuasiNewtonOptimizerv4Template ()
virtual void	ResetNewtonStep (IndexValueType location)
virtual	~QuasiNewtonOptimizerv4Template ()
Protected Member Functions inherited from itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >
	GradientDescentOptimizerv4Template ()
virtual	~GradientDescentOptimizerv4Template ()
virtual void	ModifyGradientByScalesOverSubRange (const IndexRangeType &subrange) ITK_OVERRIDE
virtual void	ModifyGradientByLearningRateOverSubRange (const IndexRangeType &subrange) ITK_OVERRIDE
Protected Member Functions inherited from itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >
	GradientDescentOptimizerBasev4Template ()
virtual	~GradientDescentOptimizerBasev4Template ()
Protected Member Functions inherited from itk::ObjectToObjectOptimizerBaseTemplate< TInternalComputationValueType >
	ObjectToObjectOptimizerBaseTemplate ()
virtual	~ObjectToObjectOptimizerBaseTemplate ()
Protected Member Functions inherited from itk::Object
	Object ()
bool	PrintObservers (std::ostream &os, Indent indent) const
virtual void	SetTimeStamp (const TimeStamp &time)
virtual	~Object ()
Protected Member Functions inherited from itk::LightObject
virtual LightObject::Pointer	InternalClone () const
	LightObject ()
virtual void	PrintHeader (std::ostream &os, Indent indent) const
virtual void	PrintTrailer (std::ostream &os, Indent indent) const
virtual	~LightObject ()

Protected Attributes
SizeValueType	m_BestIteration
ParametersType	m_BestPosition
MeasureType	m_BestValue
ParametersType	m_CurrentPosition
HessianArrayType	m_HessianArray
SizeValueType	m_MaximumIterationsWithoutProgress
TInternalComputationValueType	m_MaximumNewtonStepSizeInPhysicalUnits
DerivativeType	m_NewtonStep
std::vector< bool >	m_NewtonStepValidFlags
std::string	m_NewtonStepWarning
ParametersType	m_OptimalStep
ParametersType	m_PreviousPosition
MeasureType	m_PreviousValue
Protected Attributes inherited from itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >
ParametersType	m_BestParameters
TInternalComputationValueType	m_ConvergenceValue
MeasureType	m_CurrentBestValue
TInternalComputationValueType	m_LearningRate
TInternalComputationValueType	m_MinimumConvergenceValue
DerivativeType	m_PreviousGradient
bool	m_ReturnBestParametersAndValue
Protected Attributes inherited from itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >
ConvergenceMonitoringType::Pointer	m_ConvergenceMonitoring
SizeValueType	m_ConvergenceWindowSize
bool	m_DoEstimateLearningRateAtEachIteration
bool	m_DoEstimateLearningRateOnce
DerivativeType	m_Gradient
TInternalComputationValueType	m_MaximumStepSizeInPhysicalUnits
DomainThreader < ThreadedIndexedContainerPartitioner, Self >::Pointer	m_ModifyGradientByLearningRateThreader
DomainThreader < ThreadedIndexedContainerPartitioner, Self >::Pointer	m_ModifyGradientByScalesThreader
bool	m_Stop
StopConditionType	m_StopCondition
StopConditionDescriptionType	m_StopConditionDescription
bool	m_UseConvergenceMonitoring
Protected Attributes inherited from itk::ObjectToObjectOptimizerBaseTemplate< TInternalComputationValueType >
SizeValueType	m_CurrentIteration
MeasureType	m_CurrentMetricValue
bool	m_DoEstimateScales
MetricTypePointer	m_Metric
SizeValueType	m_NumberOfIterations
ThreadIdType	m_NumberOfThreads
ScalesType	m_Scales
bool	m_ScalesAreIdentity
ScalesEstimatorType::Pointer	m_ScalesEstimator
ScalesType	m_Weights
bool	m_WeightsAreIdentity
Protected Attributes inherited from itk::LightObject
InternalReferenceCountType	m_ReferenceCount
SimpleFastMutexLock	m_ReferenceCountLock

Private Member Functions
void	operator= (const Self &)
	QuasiNewtonOptimizerv4Template (const Self &)

Private Attributes
DomainThreader < ThreadedIndexedContainerPartitioner, Self >::Pointer	m_EstimateNewtonStepThreader

Additional Inherited Members
Protected Types inherited from itk::LightObject
typedef int	InternalReferenceCountType

Member Typedef Documentation

template<typename TInternalComputationValueType >

typedef SmartPointer< const Self > itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::ConstPointer

Definition at line 67 of file itkQuasiNewtonOptimizerv4.h.

template<typename TInternalComputationValueType >

typedef Superclass::DerivativeType itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::DerivativeType

Definition at line 80 of file itkQuasiNewtonOptimizerv4.h.

template<typename TInternalComputationValueType >

typedef std::vector<HessianType> itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::HessianArrayType

Type for an array of Hessian matrix for local support

Definition at line 88 of file itkQuasiNewtonOptimizerv4.h.

template<typename TInternalComputationValueType >

typedef itk::Array2D<TInternalComputationValueType> itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::HessianType

Type for Hessian matrix in the Quasi-Newton method

Definition at line 85 of file itkQuasiNewtonOptimizerv4.h.

template<typename TInternalComputationValueType >

typedef Superclass::IndexRangeType itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::IndexRangeType

Definition at line 81 of file itkQuasiNewtonOptimizerv4.h.

template<typename TInternalComputationValueType >

typedef TInternalComputationValueType itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::InternalComputationValueType

It should be possible to derive the internal computation type from the class object.

Definition at line 73 of file itkQuasiNewtonOptimizerv4.h.

template<typename TInternalComputationValueType >

typedef Superclass::MeasureType itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::MeasureType

Definition at line 79 of file itkQuasiNewtonOptimizerv4.h.

template<typename TInternalComputationValueType >

typedef Superclass::ParametersType itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::ParametersType

Definition at line 78 of file itkQuasiNewtonOptimizerv4.h.

template<typename TInternalComputationValueType >

typedef SmartPointer< Self > itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::Pointer

Definition at line 66 of file itkQuasiNewtonOptimizerv4.h.

template<typename TInternalComputationValueType >

typedef QuasiNewtonOptimizerv4Template itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::Self

Standard class typedefs.

Definition at line 64 of file itkQuasiNewtonOptimizerv4.h.

template<typename TInternalComputationValueType >

typedef Superclass::StopConditionType itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::StopConditionType

Definition at line 82 of file itkQuasiNewtonOptimizerv4.h.

template<typename TInternalComputationValueType >

typedef GradientDescentOptimizerv4Template<TInternalComputationValueType> itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::Superclass

Definition at line 65 of file itkQuasiNewtonOptimizerv4.h.

Constructor & Destructor Documentation

template<typename TInternalComputationValueType >

itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::QuasiNewtonOptimizerv4Template ( )

protected

template<typename TInternalComputationValueType >

virtual itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::~QuasiNewtonOptimizerv4Template ( )

protectedvirtual

template<typename TInternalComputationValueType >

itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::QuasiNewtonOptimizerv4Template ( const Self &  )

private

Member Function Documentation

template<typename TInternalComputationValueType >

virtual void itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::AdvanceOneStep ( void  )

protectedvirtual

Advance one step using the Quasi-Newton step. When the Newton step is invalid, the gradient step will be used.

Reimplemented from itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >.

template<typename TInternalComputationValueType >

void itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::CombineGradientNewtonStep ( void  )

protected

Combine a gradient step with a Newton step. The Newton step will be used when it is valid. Otherwise the gradient step will be used.

template<typename TInternalComputationValueType >

virtual bool itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::ComputeHessianAndStepWithBFGS ( IndexValueType  location )

protectedvirtual

Estimate the next Hessian and step with BFGS method. The details of the method are described at http://en.wikipedia.org/wiki/BFGS_method .

template<typename TInternalComputationValueType >

virtual::itk::LightObject::Pointer itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::CreateAnother ( void  ) const

virtual

Create an object from an instance, potentially deferring to a factory. This method allows you to create an instance of an object that is exactly the same type as the referring object. This is useful in cases where an object has been cast back to a base class.

Reimplemented from itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >.

template<typename TInternalComputationValueType >

virtual void itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::EstimateNewtonStep ( )

protectedvirtual

Estimate a Newton step

template<typename TInternalComputationValueType >

virtual void itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::EstimateNewtonStepOverSubRange ( const IndexRangeType &  subrange )

virtual

Estimate the quasi-newton step over a given index range. This function is used in QuasiNewtonOptimizerv4EstimateNewtonStepThreaderTemplate class.

template<typename TInternalComputationValueType >

virtual const char* itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::GetNameOfClass ( ) const

virtual

Run-time type information (and related methods).

Reimplemented from itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >.

template<typename TInternalComputationValueType >

virtual const DerivativeType& itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::GetNewtonStep ( ) const

virtual

Get the most recent Newton step.

template<typename TInternalComputationValueType >

void itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::ModifyCombinedNewtonStep ( )

protected

Estimate and apply the learning rate(s) for a combined Newton step. A combined Newton step uses the Newton step by default and the gradient step when the Newton step is not valid.

The learning rate is less than 1.0 and is restricted by m_MaximumNewtonStepSizeInPhysicalUnits.

template<typename TInternalComputationValueType >

static Pointer itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::New ( )

static

Method for creation through the object factory.

template<typename TInternalComputationValueType >

void itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::operator= ( const Self &  )

private

template<typename TInternalComputationValueType >

virtual void itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::PrintSelf ( std::ostream &  os, Indent  indent  ) const

protectedvirtual

Methods invoked by Print() to print information about the object including superclasses. Typically not called by the user (use Print() instead) but used in the hierarchical print process to combine the output of several classes.

Reimplemented from itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >.

template<typename TInternalComputationValueType >

virtual void itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::ResetNewtonStep ( IndexValueType  location )

protectedvirtual

Reset the Hessian to identity matrix and the Newton step to zeros.

template<typename TInternalComputationValueType >

virtual void itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::SetMaximumIterationsWithoutProgress ( SizeValueType  _arg )

virtual

Set the maximum tolerable number of iteration without any progress

template<typename TInternalComputationValueType >

virtual void itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::SetMaximumNewtonStepSizeInPhysicalUnits ( TInternalComputationValueType  _arg )

virtual

Set the maximum step size.

When SetScalesEstimator is called by user, the optimizer will compute learning rates as m_MaximumNewtonStepSizeInPhysicalUnits / m_ScalesEstimator->EstimateStepScale(newtonStep).

If SetMaximumNewtonStepSizeInPhysicalUnits is not called by user, m_MaximumNewtonStepSizeInPhysicalUnits defaults to lambda * m_ScalesEstimator->EstimateMaximumStepSize(),

where EstimateMaximumStepSize returns one voxel spacing and lambda may be in [1,5] according to our experience.

template<typename TInternalComputationValueType >

virtual void itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::StartOptimization ( bool  doOnlyInitialization = false )

virtual

Start and run the optimization

Reimplemented from itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >.

Member Data Documentation

template<typename TInternalComputationValueType >

SizeValueType itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::m_BestIteration

protected

Definition at line 137 of file itkQuasiNewtonOptimizerv4.h.

template<typename TInternalComputationValueType >

ParametersType itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::m_BestPosition

protected

Definition at line 136 of file itkQuasiNewtonOptimizerv4.h.

template<typename TInternalComputationValueType >

MeasureType itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::m_BestValue

protected

The best value so far and relevant information

Definition at line 135 of file itkQuasiNewtonOptimizerv4.h.

template<typename TInternalComputationValueType >

ParametersType itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::m_CurrentPosition

protected

The information about the current step

Definition at line 127 of file itkQuasiNewtonOptimizerv4.h.

template<typename TInternalComputationValueType >

DomainThreader<ThreadedIndexedContainerPartitioner, Self>::Pointer itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::m_EstimateNewtonStepThreader

private

Threader for Newton step estimation.

Definition at line 198 of file itkQuasiNewtonOptimizerv4.h.

template<typename TInternalComputationValueType >

HessianArrayType itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::m_HessianArray

protected

The Hessian with local support

Definition at line 149 of file itkQuasiNewtonOptimizerv4.h.

template<typename TInternalComputationValueType >

SizeValueType itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::m_MaximumIterationsWithoutProgress

protected

The maximum tolerable number of iteration without any progress

Definition at line 124 of file itkQuasiNewtonOptimizerv4.h.

template<typename TInternalComputationValueType >

TInternalComputationValueType itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::m_MaximumNewtonStepSizeInPhysicalUnits

protected

The maximum Quasi-Newton step size to restrict learning rates.

Definition at line 146 of file itkQuasiNewtonOptimizerv4.h.

template<typename TInternalComputationValueType >

DerivativeType itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::m_NewtonStep

protected

The Quasi-Newton step

Definition at line 140 of file itkQuasiNewtonOptimizerv4.h.

template<typename TInternalComputationValueType >

std::vector<bool> itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::m_NewtonStepValidFlags

protected

Valid flag for the Quasi-Newton steps

Definition at line 152 of file itkQuasiNewtonOptimizerv4.h.

template<typename TInternalComputationValueType >

std::string itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::m_NewtonStepWarning

protected

Warning message during Quasi-Newton step estimation

Definition at line 143 of file itkQuasiNewtonOptimizerv4.h.

template<typename TInternalComputationValueType >

ParametersType itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::m_OptimalStep

protected

Definition at line 128 of file itkQuasiNewtonOptimizerv4.h.

template<typename TInternalComputationValueType >

ParametersType itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::m_PreviousPosition

protected

Definition at line 132 of file itkQuasiNewtonOptimizerv4.h.

template<typename TInternalComputationValueType >

MeasureType itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >::m_PreviousValue

protected

The information about the previous step

Definition at line 131 of file itkQuasiNewtonOptimizerv4.h.

---

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

• itkQuasiNewtonOptimizerv4.h