#include <itkSPSAOptimizer.h>

Inheritance diagram for itk::SPSAOptimizer:

Collaboration diagram for itk::SPSAOptimizer:

Public Types
typedef SmartPointer< const Self >	ConstPointer
typedef SmartPointer< Self >	Pointer
typedef SPSAOptimizer	Self
enum	StopConditionType { Unknown, MaximumNumberOfIterations, BelowTolerance, MetricError }
typedef SingleValuedNonLinearOptimizer	Superclass
Public Member Functions
virtual void	AdvanceOneStep (void)
virtual ::itk::LightObject::Pointer	CreateAnother (void) const
virtual SizeValueType	GetCurrentIteration () const
virtual const DerivativeType &	GetGradient ()
virtual double	GetGradientMagnitude () const
virtual double	GetLearningRate () const
virtual const char *	GetNameOfClass () const
virtual double	GetStateOfConvergence () const
virtual StopConditionType	GetStopCondition () const
const std::string	GetStopConditionDescription () const
virtual MeasureType	GetValue (void) const
virtual MeasureType	GetValue (const ParametersType &parameters) const
virtual void	GuessParameters (SizeValueType numberOfGradientEstimates, double initialStepSize)
void	ResumeOptimization (void)
void	StartOptimization (void)
void	StopOptimization (void)

virtual void	SetSa (double _arg)
virtual double	GetSa () const
void	Seta (double a)
double	Geta ()

virtual void	SetSc (double _arg)
virtual double	GetSc () const
void	Setc (double c)
double	Getc ()

virtual void	SetA (double _arg)
virtual double	GetA () const

virtual void	SetAlpha (double _arg)
virtual double	GetAlpha () const

virtual void	SetGamma (double _arg)
virtual double	GetGamma () const

virtual bool	GetMaximize () const
virtual void	SetMaximize (bool _arg)
virtual void	MaximizeOn ()
virtual void	MaximizeOff ()
bool	GetMinimize () const
void	SetMinimize (bool v)
void	MinimizeOn ()
void	MinimizeOff ()

virtual void	SetNumberOfPerturbations (SizeValueType _arg)
virtual SizeValueType	GetNumberOfPerturbations () const

virtual void	SetStateOfConvergenceDecayRate (double _arg)
virtual double	GetStateOfConvergenceDecayRate () const

virtual void	SetMinimumNumberOfIterations (SizeValueType _arg)
virtual SizeValueType	GetMinimumNumberOfIterations () const

virtual void	SetMaximumNumberOfIterations (SizeValueType _arg)
virtual SizeValueType	GetMaximumNumberOfIterations () const

virtual void	SetTolerance (double _arg)
virtual double	GetTolerance () const
Static Public Member Functions
static Pointer	New ()
Protected Member Functions
virtual double	Compute_a (SizeValueType k) const
virtual double	Compute_c (SizeValueType k) const
virtual void	ComputeGradient (const ParametersType &parameters, DerivativeType &gradient)
virtual void	GenerateDelta (const unsigned int spaceDimension)
void	PrintSelf (std::ostream &os, Indent indent) const
	SPSAOptimizer ()
virtual	~SPSAOptimizer ()
Protected Attributes
SizeValueType	m_CurrentIteration
DerivativeType	m_Delta
Statistics::MersenneTwisterRandomVariateGenerator::Pointer	m_Generator
DerivativeType	m_Gradient
double	m_LearningRate
double	m_StateOfConvergence
bool	m_Stop
StopConditionType	m_StopCondition
Private Member Functions
void	operator= (const Self &)
	SPSAOptimizer (const Self &)
Private Attributes
double	m_A
double	m_Alpha
double	m_Gamma
double	m_GradientMagnitude
bool	m_Maximize
SizeValueType	m_MaximumNumberOfIterations
SizeValueType	m_MinimumNumberOfIterations
SizeValueType	m_NumberOfPerturbations
double	m_Sa
double	m_Sc
double	m_StateOfConvergenceDecayRate
double	m_Tolerance

Detailed Description

An optimizer based on simultaneous perturbation...

This optimizer is an implementation of the Simultaneous Perturbation Stochastic Approximation method, described in:

http://www.jhuapl.edu/SPSA/

Spall, J.C. (1998), "An Overview of the Simultaneous Perturbation Method for Efficient Optimization," Johns Hopkins APL Technical Digest, vol. 19, pp. 482-492

Definition at line 43 of file itkSPSAOptimizer.h.

Member Typedef Documentation

typedef SmartPointer< const Self > itk::SPSAOptimizer::ConstPointer

Reimplemented from itk::SingleValuedNonLinearOptimizer.

Definition at line 52 of file itkSPSAOptimizer.h.

typedef SmartPointer< Self > itk::SPSAOptimizer::Pointer

Reimplemented from itk::SingleValuedNonLinearOptimizer.

Definition at line 51 of file itkSPSAOptimizer.h.

typedef SPSAOptimizer itk::SPSAOptimizer::Self

Standard class typedefs.

Reimplemented from itk::SingleValuedNonLinearOptimizer.

Definition at line 49 of file itkSPSAOptimizer.h.

typedef SingleValuedNonLinearOptimizer itk::SPSAOptimizer::Superclass

Reimplemented from itk::SingleValuedNonLinearOptimizer.

Definition at line 50 of file itkSPSAOptimizer.h.

Member Enumeration Documentation

enum itk::SPSAOptimizer::StopConditionType

Codes of stopping conditions

Enumerator:

Unknown
MaximumNumberOfIterations
BelowTolerance
MetricError

Definition at line 61 of file itkSPSAOptimizer.h.

Constructor & Destructor Documentation

itk::SPSAOptimizer::SPSAOptimizer ( ) [protected]

virtual itk::SPSAOptimizer::~SPSAOptimizer ( ) [inline, protected, virtual]

Definition at line 213 of file itkSPSAOptimizer.h.

itk::SPSAOptimizer::SPSAOptimizer ( const Self & ) [private]

Member Function Documentation

virtual void itk::SPSAOptimizer::AdvanceOneStep ( void ) [virtual]

Advance one step following the gradient direction.

virtual double itk::SPSAOptimizer::Compute_a ( SizeValueType k ) const [protected, virtual]

Method to compute the learning rate at iteration k (a_k).

virtual double itk::SPSAOptimizer::Compute_c ( SizeValueType k ) const [protected, virtual]

Method to compute the gain factor for the perturbation at iteration k (c_k).

virtual void itk::SPSAOptimizer::ComputeGradient	(	const ParametersType &	parameters,
		DerivativeType &	gradient
	)		`[protected, virtual]`

Compute the gradient at a position. m_NumberOfPerturbations are used, and scales are taken into account.

virtual::itk::LightObject::Pointer itk::SPSAOptimizer::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::SingleValuedNonLinearOptimizer.

virtual void itk::SPSAOptimizer::GenerateDelta ( const unsigned int spaceDimension ) [protected, virtual]

Method to generate a perturbation vector. Takes scales into account.

double itk::SPSAOptimizer::Geta ( ) [inline]

Set/Get a.

Definition at line 125 of file itkSPSAOptimizer.h.

virtual double itk::SPSAOptimizer::GetA ( ) const [virtual]

Set/Get A.

virtual double itk::SPSAOptimizer::GetAlpha ( ) const [virtual]

Set/Get alpha.

double itk::SPSAOptimizer::Getc ( ) [inline]

Set/Get c.

Definition at line 133 of file itkSPSAOptimizer.h.

virtual SizeValueType itk::SPSAOptimizer::GetCurrentIteration ( ) const [virtual]

Get the current iteration number.

virtual double itk::SPSAOptimizer::GetGamma ( ) const [virtual]

Set/Get gamma.

virtual const DerivativeType& itk::SPSAOptimizer::GetGradient ( ) [virtual]

Get the latest computed gradient

virtual double itk::SPSAOptimizer::GetGradientMagnitude ( ) const [virtual]

Get the GradientMagnitude of the latest computed gradient

virtual double itk::SPSAOptimizer::GetLearningRate ( ) const [virtual]

Get the current LearningRate (a_k)

virtual bool itk::SPSAOptimizer::GetMaximize ( ) const [virtual]

Methods to configure the cost function.

virtual SizeValueType itk::SPSAOptimizer::GetMaximumNumberOfIterations ( ) const [virtual]

Set/Get the maximum number of iterations.

bool itk::SPSAOptimizer::GetMinimize ( ) const [inline]

Methods to configure the cost function.

Definition at line 155 of file itkSPSAOptimizer.h.

virtual SizeValueType itk::SPSAOptimizer::GetMinimumNumberOfIterations ( ) const [virtual]

Set/Get the minimum number of iterations

virtual const char* itk::SPSAOptimizer::GetNameOfClass ( ) const [virtual]

Run-time type information (and related methods).

Reimplemented from itk::SingleValuedNonLinearOptimizer.

virtual SizeValueType itk::SPSAOptimizer::GetNumberOfPerturbations ( ) const [virtual]

Set/Get the number of perturbation used to construct a gradient estimate g_k. q = NumberOfPerturbations g_k = 1/q sum_{j=1..q} g^(j)_k

virtual double itk::SPSAOptimizer::GetSa ( ) const [virtual]

Set/Get a.

virtual double itk::SPSAOptimizer::GetSc ( ) const [virtual]

Set/Get c.

virtual double itk::SPSAOptimizer::GetStateOfConvergence ( ) const [virtual]

Get the state of convergence in the last iteration. When the StateOfConvergence is lower than the Tolerance, and the minimum number of iterations has been performed, the optimization stops.

The state of convergence (SOC) is initialized with 0.0 and updated after each iteration as follows: SOC *= SOCDecayRate SOC += a_k * GradientMagnitude

virtual double itk::SPSAOptimizer::GetStateOfConvergenceDecayRate ( ) const [virtual]

Set/Get StateOfConvergenceDecayRate (number between 0 and 1).

virtual StopConditionType itk::SPSAOptimizer::GetStopCondition ( ) const [virtual]

Get Stop condition.

const std::string itk::SPSAOptimizer::GetStopConditionDescription ( ) const [virtual]

Get the reason for termination

Reimplemented from itk::Optimizer.

virtual double itk::SPSAOptimizer::GetTolerance ( ) const [virtual]

Set/Get Tolerance

virtual MeasureType itk::SPSAOptimizer::GetValue ( void ) const [virtual]

Get the cost function value at the current position.

virtual MeasureType itk::SPSAOptimizer::GetValue ( const ParametersType & parameters ) const [virtual]

Get the cost function value at any position

Reimplemented from itk::SingleValuedNonLinearOptimizer.

virtual void itk::SPSAOptimizer::GuessParameters	(	SizeValueType	numberOfGradientEstimates,
		double	initialStepSize
	)		`[virtual]`

Guess the parameters a and A. This function needs the number of GradientEstimates used for estimating a and A and and the expected initial step size (where step size is defined as the maximum of the absolute values of the parameter update). Make sure you set c, Alpha, Gamma, the MaximumNumberOfIterations, the Scales, and the the InitialPosition before calling this method.

Described in: Spall, J.C. (1998), "Implementation of the Simultaneous Perturbation Algorithm for Stochastic Optimization", IEEE Trans. Aerosp. Electron. Syst. 34(3), 817-823.

virtual void itk::SPSAOptimizer::MaximizeOff ( ) [virtual]

Methods to configure the cost function.

virtual void itk::SPSAOptimizer::MaximizeOn ( ) [virtual]

Methods to configure the cost function.

void itk::SPSAOptimizer::MinimizeOff ( ) [inline]

Methods to configure the cost function.

Definition at line 161 of file itkSPSAOptimizer.h.

void itk::SPSAOptimizer::MinimizeOn ( ) [inline]

Methods to configure the cost function.

Definition at line 159 of file itkSPSAOptimizer.h.

static Pointer itk::SPSAOptimizer::New ( ) [static]

Method for creation through the object factory.

Reimplemented from itk::SingleValuedNonLinearOptimizer.

void itk::SPSAOptimizer::operator= ( const Self & ) [private]

Types inherited from the superclass

Reimplemented from itk::SingleValuedNonLinearOptimizer.

void itk::SPSAOptimizer::PrintSelf	(	std::ostream &	os,
		Indent	indent
	)		const `[protected, virtual]`

PrintSelf method.

Reimplemented from itk::SingleValuedNonLinearOptimizer.

void itk::SPSAOptimizer::ResumeOptimization ( void )

Resume previously stopped optimization with current parameters

See also:: StopOptimization.

void itk::SPSAOptimizer::Seta ( double a ) [inline]

Set/Get a.

Definition at line 124 of file itkSPSAOptimizer.h.

virtual void itk::SPSAOptimizer::SetA ( double _arg ) [virtual]

Set/Get A.

virtual void itk::SPSAOptimizer::SetAlpha ( double _arg ) [virtual]

Set/Get alpha.

void itk::SPSAOptimizer::Setc ( double c ) [inline]

Set/Get c.

Definition at line 132 of file itkSPSAOptimizer.h.

virtual void itk::SPSAOptimizer::SetGamma ( double _arg ) [virtual]

Set/Get gamma.

virtual void itk::SPSAOptimizer::SetMaximize ( bool _arg ) [virtual]

Methods to configure the cost function.

virtual void itk::SPSAOptimizer::SetMaximumNumberOfIterations ( SizeValueType _arg ) [virtual]

Set/Get the maximum number of iterations.

void itk::SPSAOptimizer::SetMinimize ( bool v ) [inline]

Methods to configure the cost function.

Definition at line 157 of file itkSPSAOptimizer.h.

virtual void itk::SPSAOptimizer::SetMinimumNumberOfIterations ( SizeValueType _arg ) [virtual]

Set/Get the minimum number of iterations

virtual void itk::SPSAOptimizer::SetNumberOfPerturbations ( SizeValueType _arg ) [virtual]

Set/Get the number of perturbation used to construct a gradient estimate g_k. q = NumberOfPerturbations g_k = 1/q sum_{j=1..q} g^(j)_k

virtual void itk::SPSAOptimizer::SetSa ( double _arg ) [virtual]

Set/Get a.

virtual void itk::SPSAOptimizer::SetSc ( double _arg ) [virtual]

Set/Get c.

virtual void itk::SPSAOptimizer::SetStateOfConvergenceDecayRate ( double _arg ) [virtual]

Set/Get StateOfConvergenceDecayRate (number between 0 and 1).

virtual void itk::SPSAOptimizer::SetTolerance ( double _arg ) [virtual]

Set/Get Tolerance

void itk::SPSAOptimizer::StartOptimization ( void ) [virtual]

Start optimization.

Reimplemented from itk::Optimizer.

void itk::SPSAOptimizer::StopOptimization ( void )

Stop optimization.

See also:: ResumeOptimization

Member Data Documentation

double itk::SPSAOptimizer::m_A [private]

Definition at line 273 of file itkSPSAOptimizer.h.

double itk::SPSAOptimizer::m_Alpha [private]

Definition at line 274 of file itkSPSAOptimizer.h.

SizeValueType itk::SPSAOptimizer::m_CurrentIteration [protected]

Definition at line 231 of file itkSPSAOptimizer.h.

DerivativeType itk::SPSAOptimizer::m_Delta [protected]

Definition at line 223 of file itkSPSAOptimizer.h.

double itk::SPSAOptimizer::m_Gamma [private]

Definition at line 275 of file itkSPSAOptimizer.h.

Statistics::MersenneTwisterRandomVariateGenerator::Pointer itk::SPSAOptimizer::m_Generator [protected]

Random number generator

Definition at line 234 of file itkSPSAOptimizer.h.

DerivativeType itk::SPSAOptimizer::m_Gradient [protected]

Variables updated during optimization

Definition at line 219 of file itkSPSAOptimizer.h.

double itk::SPSAOptimizer::m_GradientMagnitude [private]

Definition at line 267 of file itkSPSAOptimizer.h.

double itk::SPSAOptimizer::m_LearningRate [protected]

Definition at line 221 of file itkSPSAOptimizer.h.

bool itk::SPSAOptimizer::m_Maximize [private]

Definition at line 266 of file itkSPSAOptimizer.h.

SizeValueType itk::SPSAOptimizer::m_MaximumNumberOfIterations [private]

Definition at line 263 of file itkSPSAOptimizer.h.

SizeValueType itk::SPSAOptimizer::m_MinimumNumberOfIterations [private]

Settings.

Definition at line 262 of file itkSPSAOptimizer.h.

SizeValueType itk::SPSAOptimizer::m_NumberOfPerturbations [private]

Definition at line 268 of file itkSPSAOptimizer.h.

double itk::SPSAOptimizer::m_Sa [private]

Parameters, as described by Spall.

Definition at line 271 of file itkSPSAOptimizer.h.

double itk::SPSAOptimizer::m_Sc [private]

Definition at line 272 of file itkSPSAOptimizer.h.

double itk::SPSAOptimizer::m_StateOfConvergence [protected]

Definition at line 229 of file itkSPSAOptimizer.h.

double itk::SPSAOptimizer::m_StateOfConvergenceDecayRate [private]

Definition at line 264 of file itkSPSAOptimizer.h.

bool itk::SPSAOptimizer::m_Stop [protected]

Definition at line 225 of file itkSPSAOptimizer.h.

StopConditionType itk::SPSAOptimizer::m_StopCondition [protected]

Definition at line 227 of file itkSPSAOptimizer.h.

double itk::SPSAOptimizer::m_Tolerance [private]

Definition at line 265 of file itkSPSAOptimizer.h.

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

itkSPSAOptimizer.h

Public Types

Public Member Functions

Static Public Member Functions

Protected Member Functions

Protected Attributes

Private Member Functions

Private Attributes

Detailed Description

Member Typedef Documentation

Member Enumeration Documentation

Constructor & Destructor Documentation

Member Function Documentation

Member Data Documentation