Numerical_gradient< Model > Class Template Reference

Approximates the gradient and/or curvature of a target distribution, evaluated at a certain location. The user must provide the mechanisms to change the model (see constructor). More...

#include <sample_default.h>

Inheritance diagram for Numerical_gradient< Model >:

Public Types
typedef Model_evaluator< Model > ::Type	Target_distribution
typedef Move_model_parameter < Model >::Type	Move_parameter
typedef Model_parameter_evaluator < Model >::Type	Get_neighborhood
typedef Model_dimension< Model > ::Type	Get_dimension

Public Member Functions
	Numerical_gradient (const Target_distribution &log_target, const Move_parameter &move_param, const Get_neighborhood &get_neighbors, const Get_dimension &get_dim)
	Construct a gradient approximation functor. More...
kjb::Vector	operator() (const Model &q) const
	Evaluates gradient at q. More...
kjb::Vector	curvature (const Model &q) const
kjb::Vector	gradient (const Model &q) const
void	gradient_and_curvature (const Model &q, kjb::Vector &gradient, kjb::Vector &curvature) const

Detailed Description

template<typename Model>
class Numerical_gradient< Model >

Approximates the gradient and/or curvature of a target distribution, evaluated at a certain location. The user must provide the mechanisms to change the model (see constructor).

Note

curvature is only computed in the direction of the axes.

Member Typedef Documentation

template<typename Model >

typedef Model_dimension<Model>::Type Numerical_gradient< Model >::Get_dimension

template<typename Model >

typedef Model_parameter_evaluator<Model>::Type Numerical_gradient< Model >::Get_neighborhood

template<typename Model >

typedef Move_model_parameter<Model>::Type Numerical_gradient< Model >::Move_parameter

template<typename Model >

typedef Model_evaluator<Model>::Type Numerical_gradient< Model >::Target_distribution

Constructor & Destructor Documentation

template<typename Model >

Numerical_gradient< Model >::Numerical_gradient ( const Target_distribution &  log_target, const Move_parameter &  move_param, const Get_neighborhood &  get_neighbors, const Get_dimension &  get_dim  )

inline

Construct a gradient approximation functor.

Parameters

log_target	The log of the target distribution.
move_param	Mechanism to 'move' a parameter of the model by a delta.
get_neighbors	Mechamisn to get the neighborhood of the current model location. We allow this to be a function of the current model.
get_dim	Mechanism to obtain the dimension of the model.

Member Function Documentation

template<typename Model >

kjb::Vector Numerical_gradient< Model >::curvature ( const Model &  q ) const

inline

template<typename Model >

kjb::Vector Numerical_gradient< Model >::gradient ( const Model &  q ) const

inline

template<typename Model >

void Numerical_gradient< Model >::gradient_and_curvature ( const Model &  q, kjb::Vector &  gradient, kjb::Vector &  curvature  ) const

inline

template<typename Model >

kjb::Vector Numerical_gradient< Model >::operator() ( const Model &  q ) const

inline

Evaluates gradient at q.

---

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

• /work/kobus/src/lib/sample_cpp/sample_default.h