Squared exponential kernel with noise inference. More...

#include <kernels.hpp>

Inheritance diagram for gplib::kernels::squared_exponential:

Collaboration diagram for gplib::kernels::squared_exponential:

Classes
struct	implementation

Public Member Functions
	squared_exponential ()
	Constructor. More...

	squared_exponential (const std::vector< double > &params)
	Constructor, requires the hyperparameter. More...

	~squared_exponential ()
	Destructor. More...

arma::mat	eval (const arma::mat &X, const arma::mat &Y, bool diag=false) const
	Evaluates the kernel function over the provided matrices. More...

arma::mat	derivate (size_t param_id, const arma::mat &X, const arma::mat &Y, bool diag=false) const
	Returns the value of the derivative wrt a certain parameter with a a particular pair of input matrices. More...

size_t	n_params () const
	Returns the number of params needed by the kernel. More...

void	set_params (const std::vector< double > &params)
	Sets the parameters of the kernel using the proided vector. More...

void	set_lower_bounds (const std::vector< double > &lower_bounds)
	Sets the lower bounds to be used by the kernel during training process. More...

void	set_upper_bounds (const std::vector< double > &upper_bounds)
	Sets the upper bounds to be used by the kernel during training process. More...

std::vector< double >	get_params () const
	Returns a vector with the current values of the parameters of the kernel. More...

std::vector< double >	get_lower_bounds () const
	Returns a vector with the current values of the lower_bounds for each of the parameters of the kernel. More...

std::vector< double >	get_upper_bounds () const
	Returns a vector with the current values of the upper_bounds for each of the parameters of the kernel. More...

Public Member Functions inherited from gplib::kernel_class
	kernel_class ()
	Kernel Class definition. More...

virtual	~kernel_class ()=default
	Destructor. More...

Private Attributes
implementation *	pimpl

Detailed Description

Squared exponential kernel with noise inference.

This kernel is defined as: sig ^ 2 * exp(- ((x - xp) * (x - xp)')/ 2 * l) + sig_noise ^ 2 * I

Note: params : vector of hyperparameters 0 : sig, 1 : l (length scale), 2 : sig_noise.

Constructor & Destructor Documentation

gplib::kernels::squared_exponential::squared_exponential ( )

Constructor.

gplib::kernels::squared_exponential::squared_exponential ( const std::vector< double > & params )

Constructor, requires the hyperparameter.

Parameters

params : Vector of hyperparameters

gplib::kernels::squared_exponential::~squared_exponential ( )

Destructor.

Member Function Documentation

mat gplib::kernels::squared_exponential::derivate	(	size_t	param_id,
		const arma::mat &	X,
		const arma::mat &	Y,
		bool	diag = `false`
	)		const

virtual

Returns the value of the derivative wrt a certain parameter with a a particular pair of input matrices.

Parameters

param_id	: Identifier of the parameter we are derivating with respect to.
X	: First matrix for derivative evaluation.
Y	: Second matrix for derivative evaluation.
diag	: Flag, if it is true the kernel should only be evaluated for the derivative entries pertaining to the diagonal of the answer matrix, this is due to performance reasons while using FITC.

Implements gplib::kernel_class.

mat gplib::kernels::squared_exponential::eval	(	const arma::mat &	X,
		const arma::mat &	Y,
		bool	diag = `false`
	)		const

virtual

Evaluates the kernel function over the provided matrices.

Parameters

X	: First matrix for kernel evaluation.
Y	: Second matrix for kernel evaluation.
diag	: Flag, if it is true the kernel should only be evaluated for the entries pertaining to the diagonal of the answer matrix, this is due to performance reasons while using FITC.

Implements gplib::kernel_class.

vector< double > gplib::kernels::squared_exponential::get_lower_bounds ( ) const

virtual

Returns a vector with the current values of the lower_bounds for each of the parameters of the kernel.

Implements gplib::kernel_class.

vector< double > gplib::kernels::squared_exponential::get_params ( ) const

virtual

Returns a vector with the current values of the parameters of the kernel.

Implements gplib::kernel_class.

vector< double > gplib::kernels::squared_exponential::get_upper_bounds ( ) const

virtual

Returns a vector with the current values of the upper_bounds for each of the parameters of the kernel.