itk::LBFGSOptimizer Class Reference
[Numerics, Optimizers]

Wrap of the vnl_lbfgs algorithm. More...

#include <itkLBFGSOptimizer.h>

Inheritance diagram for itk::LBFGSOptimizer:

[legend]Collaboration diagram for itk::LBFGSOptimizer:

[legend]List of all members.

Public Types
typedef LBFGSOptimizer	Self
typedef SingleValuedNonLinearVnlOptimizer	Superclass
typedef SmartPointer< Self >	Pointer
typedef SmartPointer< const Self >	ConstPointer
typedef vnl_vector< double >	InternalParametersType
typedef vnl_lbfgs	InternalOptimizerType
Public Member Functions
virtual const char *	GetClassName () const
vnl_lbfgs *	GetOptimizer (void)
void	StartOptimization (void)
virtual void	SetCostFunction (SingleValuedCostFunction *costFunction)
virtual void	SetTrace (bool flag)
virtual bool	GetTrace ()
virtual void	TraceOn ()
virtual void	TraceOff ()
virtual void	SetMaximumNumberOfFunctionEvaluations (unsigned int n)
virtual unsigned int	GetMaximumNumberOfFunctionEvaluations ()
virtual void	SetGradientConvergenceTolerance (double gtol)
virtual double	GetGradientConvergenceTolerance ()
virtual void	SetLineSearchAccuracy (double tol)
virtual double	GetLineSearchAccuracy ()
virtual void	SetDefaultStepLength (double stp)
virtual double	GetDefaultStepLength ()
Static Public Member Functions
Pointer	New ()
Protected Types
typedef Superclass::CostFunctionAdaptorType	CostFunctionAdaptorType
Protected Member Functions
	LBFGSOptimizer ()
virtual	~LBFGSOptimizer ()
void	PrintSelf (std::ostream &os, Indent indent) const

---

Detailed Description

Wrap of the vnl_lbfgs algorithm.

Definition at line 31 of file itkLBFGSOptimizer.h.

---

Member Typedef Documentation

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

Reimplemented from itk::SingleValuedNonLinearVnlOptimizer. Definition at line 39 of file itkLBFGSOptimizer.h.

typedef Superclass::CostFunctionAdaptorType itk::LBFGSOptimizer::CostFunctionAdaptorType [protected]

Reimplemented from itk::SingleValuedNonLinearVnlOptimizer. Definition at line 107 of file itkLBFGSOptimizer.h.

typedef vnl_lbfgs itk::LBFGSOptimizer::InternalOptimizerType

Internal optimizer type. Definition at line 51 of file itkLBFGSOptimizer.h.

typedef vnl_vector<double> itk::LBFGSOptimizer::InternalParametersType

InternalParameters typedef. Definition at line 48 of file itkLBFGSOptimizer.h.

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

Reimplemented from itk::SingleValuedNonLinearVnlOptimizer. Definition at line 38 of file itkLBFGSOptimizer.h.

typedef LBFGSOptimizer itk::LBFGSOptimizer::Self

Standard "Self" typedef. Reimplemented from itk::SingleValuedNonLinearVnlOptimizer. Definition at line 36 of file itkLBFGSOptimizer.h.

typedef SingleValuedNonLinearVnlOptimizer itk::LBFGSOptimizer::Superclass

Reimplemented from itk::SingleValuedNonLinearVnlOptimizer. Definition at line 37 of file itkLBFGSOptimizer.h.

---

Constructor & Destructor Documentation

itk::LBFGSOptimizer::LBFGSOptimizer (   )  [protected]

virtual itk::LBFGSOptimizer::~LBFGSOptimizer (   )  [protected, virtual]

---

Member Function Documentation

virtual const char* itk::LBFGSOptimizer::GetClassName (   )  const [virtual]

Run-time type information (and related methods). Reimplemented from itk::SingleValuedNonLinearVnlOptimizer.

virtual double itk::LBFGSOptimizer::GetDefaultStepLength (   )  [virtual]

Set/Get the default step size. This is a positive real number with a default value of 1.0 which determines the stpe size in the line search.

virtual double itk::LBFGSOptimizer::GetGradientConvergenceTolerance (   )  [virtual]

Set/Get the gradient convergence tolerance. This is a positive real number that determines the accuracy with which the solution is to be found. The optimization terminates when: ||G|| < gtol max(1,||X||) where ||.|| denotes the Euclidean norm.

virtual double itk::LBFGSOptimizer::GetLineSearchAccuracy (   )  [virtual]

Set/Get the line search accuracy. This is a positive real number with a default value of 0.9, which controls the accuracy of the line search. If the function and gradient evalutions are inexpensive with respect to the cost of the iterations it may be advantageous to set the value to a small value (say 0.1).

virtual unsigned int itk::LBFGSOptimizer::GetMaximumNumberOfFunctionEvaluations (   )  [virtual]

Set/Get the maximum number of function evaluations allowed.

vnl_lbfgs* itk::LBFGSOptimizer::GetOptimizer (  void   )

Method for getting access to the internal optimizer.

virtual bool itk::LBFGSOptimizer::GetTrace (   )  [virtual]

Set/Get the optimizer trace flag. If set to true, the optimizer prints out information every iteration.

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

Method for creation through the object factory. Reimplemented from itk::SingleValuedNonLinearOptimizer.

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

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::SingleValuedNonLinearOptimizer.

virtual void itk::LBFGSOptimizer::SetCostFunction (  SingleValuedCostFunction *  costFunction  )  [virtual]

Plug in a Cost Function into the optimizer Implements itk::SingleValuedNonLinearVnlOptimizer.

virtual void itk::LBFGSOptimizer::SetDefaultStepLength (  double  stp  )  [virtual]

Set/Get the default step size. This is a positive real number with a default value of 1.0 which determines the stpe size in the line search.

virtual void itk::LBFGSOptimizer::SetGradientConvergenceTolerance (  double  gtol  )  [virtual]

Set/Get the gradient convergence tolerance. This is a positive real number that determines the accuracy with which the solution is to be found. The optimization terminates when: ||G|| < gtol max(1,||X||) where ||.|| denotes the Euclidean norm.

virtual void itk::LBFGSOptimizer::SetLineSearchAccuracy (  double  tol  )  [virtual]

Set/Get the line search accuracy. This is a positive real number with a default value of 0.9, which controls the accuracy of the line search. If the function and gradient evalutions are inexpensive with respect to the cost of the iterations it may be advantageous to set the value to a small value (say 0.1).

virtual void itk::LBFGSOptimizer::SetMaximumNumberOfFunctionEvaluations (  unsigned int  n  )  [virtual]

Set/Get the maximum number of function evaluations allowed.

virtual void itk::LBFGSOptimizer::SetTrace (  bool  flag  )  [virtual]

Set/Get the optimizer trace flag. If set to true, the optimizer prints out information every iteration.

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

Start optimization with an initial value. Reimplemented from itk::Optimizer.

virtual void itk::LBFGSOptimizer::TraceOff (   )  [virtual]

Set/Get the optimizer trace flag. If set to true, the optimizer prints out information every iteration.

virtual void itk::LBFGSOptimizer::TraceOn (   )  [virtual]

Set/Get the optimizer trace flag. If set to true, the optimizer prints out information every iteration.

---

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

• itkLBFGSOptimizer.h

---