详细描述

The Inference Method base class.

The Inference Method computes (a Gaussian approximation to) the posterior distribution for a given Gaussian Process.

It is possible to sample the (true) log-marginal likelihood on the base of any implemented approximation. See CInferenceMethod::get_marginal_likelihood_estimate.

在文件 InferenceMethod.h 第 81 行定义.

类 CInferenceMethod 继承关系图:

[图例]

Public 成员函数
	CInferenceMethod ()

	CInferenceMethod (CKernel kernel, CFeatures features, CMeanFunction mean, CLabels labels, CLikelihoodModel *model)

virtual	~CInferenceMethod ()

virtual EInferenceType	get_inference_type () const

virtual float64_t	get_negative_log_marginal_likelihood ()=0

float64_t	get_marginal_likelihood_estimate (int32_t num_importance_samples=1, float64_t ridge_size=1e-15)

virtual CMap< TParameter , SGVector< float64_t > >	get_negative_log_marginal_likelihood_derivatives (CMap< TParameter , CSGObject > *parameters)

virtual SGVector< float64_t >	get_posterior_mean ()=0

virtual SGMatrix< float64_t >	get_posterior_covariance ()=0

virtual CMap< TParameter , SGVector< float64_t > >	get_gradient (CMap< TParameter , CSGObject > *parameters)

virtual SGVector< float64_t >	get_value ()

virtual CFeatures *	get_features ()

virtual void	set_features (CFeatures *feat)

virtual CKernel *	get_kernel ()

virtual void	set_kernel (CKernel *kern)

virtual CMeanFunction *	get_mean ()

virtual void	set_mean (CMeanFunction *m)

virtual CLabels *	get_labels ()

virtual void	set_labels (CLabels *lab)

CLikelihoodModel *	get_model ()

virtual void	set_model (CLikelihoodModel *mod)

virtual float64_t	get_scale () const

virtual void	set_scale (float64_t scale)

virtual bool	supports_regression () const

virtual bool	supports_binary () const

virtual bool	supports_multiclass () const

virtual void	update ()

virtual SGMatrix< float64_t >	get_multiclass_E ()

virtual CSGObject *	shallow_copy () const

virtual CSGObject *	deep_copy () const

virtual const char *	get_name () const =0

virtual bool	is_generic (EPrimitiveType *generic) const

template<class T >
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

template<>
void	set_generic ()

void	unset_generic ()

virtual void	print_serializable (const char *prefix="")

virtual bool	save_serializable (CSerializableFile file, const char prefix="")

virtual bool	load_serializable (CSerializableFile file, const char prefix="")

void	set_global_io (SGIO *io)

SGIO *	get_global_io ()

void	set_global_parallel (Parallel *parallel)

Parallel *	get_global_parallel ()

void	set_global_version (Version *version)

Version *	get_global_version ()

SGStringList< char >	get_modelsel_names ()

void	print_modsel_params ()

char *	get_modsel_param_descr (const char *param_name)

index_t	get_modsel_param_index (const char *param_name)

void	build_gradient_parameter_dictionary (CMap< TParameter , CSGObject > *dict)

virtual void	update_parameter_hash ()

virtual bool	parameter_hash_changed ()

virtual bool	equals (CSGObject *other, float64_t accuracy=0.0, bool tolerant=false)

virtual CSGObject *	clone ()

Public 属性
SGIO *	io

Parallel *	parallel

Version *	version

Parameter *	m_parameters

Parameter *	m_model_selection_parameters

Parameter *	m_gradient_parameters

uint32_t	m_hash

Protected 成员函数
virtual void	check_members () const

virtual void	update_alpha ()=0

virtual void	update_chol ()=0

virtual void	update_deriv ()=0

virtual void	update_train_kernel ()

virtual SGVector< float64_t >	get_derivative_wrt_inference_method (const TParameter *param)=0

virtual SGVector< float64_t >	get_derivative_wrt_likelihood_model (const TParameter *param)=0

virtual SGVector< float64_t >	get_derivative_wrt_kernel (const TParameter *param)=0

virtual SGVector< float64_t >	get_derivative_wrt_mean (const TParameter *param)=0

virtual void	compute_gradient ()

virtual void	load_serializable_pre () throw (ShogunException)

virtual void	load_serializable_post () throw (ShogunException)

virtual void	save_serializable_pre () throw (ShogunException)

virtual void	save_serializable_post () throw (ShogunException)

静态 Protected 成员函数
static void *	get_derivative_helper (void *p)

Protected 属性
CKernel *	m_kernel

CMeanFunction *	m_mean

CLikelihoodModel *	m_model

CFeatures *	m_features

CLabels *	m_labels

SGVector< float64_t >	m_alpha

SGMatrix< float64_t >	m_L

float64_t	m_log_scale

SGMatrix< float64_t >	m_ktrtr

SGMatrix< float64_t >	m_E

bool	m_gradient_update

构造及析构函数说明

CInferenceMethod ( )

default constructor

在文件 InferenceMethod.cpp 第 56 行定义.

CInferenceMethod	(	CKernel *	kernel,
		CFeatures *	features,
		CMeanFunction *	mean,
		CLabels *	labels,
		CLikelihoodModel *	model
	)

constructor

参数

kernel	covariance function
features	features to use in inference
mean	mean function
labels	labels of the features
model	likelihood model to use

在文件 InferenceMethod.cpp 第 80 行定义.

~CInferenceMethod ( )

virtual

在文件 InferenceMethod.cpp 第 92 行定义.

成员函数说明

void build_gradient_parameter_dictionary ( CMap< TParameter *, CSGObject * > * dict )

inherited

Builds a dictionary of all parameters in SGObject as well of those of SGObjects that are parameters of this object. Dictionary maps parameters to the objects that own them.

参数

dict	dictionary of parameters to be built.

在文件 SGObject.cpp 第 597 行定义.

void check_members ( ) const

protectedvirtual

check if members of object are valid for inference

被 CSparseInferenceBase, CExactInferenceMethod, CFITCInferenceMethod, CSparseVGInferenceMethod , 以及 CMultiLaplacianInferenceMethod 重载.

在文件 InferenceMethod.cpp 第 309 行定义.

CSGObject * clone ( )

virtualinherited

Creates a clone of the current object. This is done via recursively traversing all parameters, which corresponds to a deep copy. Calling equals on the cloned object always returns true although none of the memory of both objects overlaps.

返回: an identical copy of the given object, which is disjoint in memory. NULL if the clone fails. Note that the returned object is SG_REF'ed

在文件 SGObject.cpp 第 714 行定义.

void compute_gradient ( )

protectedvirtual

update gradients

被 CKLInferenceMethod, CExactInferenceMethod, CEPInferenceMethod, CSparseVGInferenceMethod, CSingleFITCLaplacianInferenceMethod, CFITCInferenceMethod , 以及 CLaplacianInferenceBase 重载.

在文件 InferenceMethod.cpp 第 330 行定义.

CSGObject * deep_copy ( ) const

virtualinherited

A deep copy. All the instance variables will also be copied.

在文件 SGObject.cpp 第 198 行定义.

bool equals	(	CSGObject *	other,
		float64_t	accuracy = `0.0`,
		bool	tolerant = `false`
	)

virtualinherited

Recursively compares the current SGObject to another one. Compares all registered numerical parameters, recursion upon complex (SGObject) parameters. Does not compare pointers!

May be overwritten but please do with care! Should not be necessary in most cases.

参数

other	object to compare with
accuracy	accuracy to use for comparison (optional)
tolerant	allows linient check on float equality (within accuracy)

返回: true if all parameters were equal, false if not

在文件 SGObject.cpp 第 618 行定义.

void * get_derivative_helper ( void * p )

staticprotected

pthread helper method to compute negative log marginal likelihood derivatives wrt hyperparameter

在文件 InferenceMethod.cpp 第 255 行定义.

virtual SGVector<float64_t> get_derivative_wrt_inference_method ( const TParameter * param )

protectedpure virtual

returns derivative of negative log marginal likelihood wrt parameter of CInferenceMethod class

参数

param parameter of CInferenceMethod class

返回: derivative of negative log marginal likelihood

在 CKLInferenceMethod, CEPInferenceMethod, CSingleFITCLaplacianInferenceMethod, CSparseInferenceBase, CExactInferenceMethod, CMultiLaplacianInferenceMethod, CSingleLaplacianInferenceMethod , 以及 CSingleSparseInferenceBase 内被实现.

virtual SGVector<float64_t> get_derivative_wrt_kernel ( const TParameter * param )

protectedpure virtual

returns derivative of negative log marginal likelihood wrt kernel's parameter

参数

param parameter of given kernel

返回: derivative of negative log marginal likelihood

在 CKLInferenceMethod, CEPInferenceMethod, CSingleFITCLaplacianInferenceMethod, CSparseInferenceBase, CExactInferenceMethod, CMultiLaplacianInferenceMethod, CSingleLaplacianInferenceMethod , 以及 CSingleSparseInferenceBase 内被实现.

virtual SGVector<float64_t> get_derivative_wrt_likelihood_model ( const TParameter * param )

protectedpure virtual

returns derivative of negative log marginal likelihood wrt parameter of likelihood model

参数

param parameter of given likelihood model

返回: derivative of negative log marginal likelihood

在 CKLInferenceMethod, CEPInferenceMethod, CSingleFITCLaplacianInferenceMethod, CSparseInferenceBase, CExactInferenceMethod, CSingleFITCLaplacianBase, CFITCInferenceMethod, CMultiLaplacianInferenceMethod, CSparseVGInferenceMethod , 以及 CSingleLaplacianInferenceMethod 内被实现.

virtual SGVector<float64_t> get_derivative_wrt_mean ( const TParameter * param )

protectedpure virtual

returns derivative of negative log marginal likelihood wrt mean function's parameter

参数

param parameter of given mean function

返回: derivative of negative log marginal likelihood

在 CKLInferenceMethod, CEPInferenceMethod, CSingleFITCLaplacianInferenceMethod, CSparseInferenceBase, CExactInferenceMethod, CSparseVGInferenceMethod, CSingleFITCLaplacianBase, CMultiLaplacianInferenceMethod , 以及 CSingleLaplacianInferenceMethod 内被实现.

virtual CFeatures* get_features ( )

virtual

get features

返回: features

在文件 InferenceMethod.h 第 266 行定义.

SGIO * get_global_io ( )

inherited

get the io object

返回: io object

在文件 SGObject.cpp 第 235 行定义.

Parallel * get_global_parallel ( )

inherited

get the parallel object

返回: parallel object

在文件 SGObject.cpp 第 277 行定义.

Version * get_global_version ( )

inherited

get the version object

返回: version object

在文件 SGObject.cpp 第 290 行定义.

virtual CMap<TParameter*, SGVector<float64_t> >* get_gradient ( CMap< TParameter *, CSGObject * > * parameters )

virtual

get the gradient

参数

parameters parameter's dictionary

返回: map of gradient. Keys are names of parameters, values are values of derivative with respect to that parameter.

实现了 CDifferentiableFunction.

在文件 InferenceMethod.h 第 245 行定义.

virtual EInferenceType get_inference_type ( ) const

virtual

return what type of inference we are, e.g. exact, FITC, Laplacian, etc.

返回: inference type

被 CKLApproxDiagonalInferenceMethod, CKLCholeskyInferenceMethod, CKLCovarianceInferenceMethod, CMultiLaplacianInferenceMethod, CKLInferenceMethod, CSparseInferenceBase, CKLDualInferenceMethod, CSingleFITCLaplacianInferenceMethod, CExactInferenceMethod, CFITCInferenceMethod, CSparseVGInferenceMethod, CEPInferenceMethod, CLaplacianInferenceBase , 以及 CSingleLaplacianInferenceMethod 重载.

在文件 InferenceMethod.h 第 104 行定义.

virtual CKernel* get_kernel ( )

virtual

get kernel

返回: kernel

在文件 InferenceMethod.h 第 283 行定义.

virtual CLabels* get_labels ( )

virtual

get labels

返回: labels

在文件 InferenceMethod.h 第 317 行定义.

float64_t get_marginal_likelihood_estimate	(	int32_t	num_importance_samples = `1`,
		float64_t	ridge_size = `1e-15`
	)

Computes an unbiased estimate of the marginal-likelihood (in log-domain),

\[ p(y|X,\theta), \]

where $y$ are the labels, $X$ are the features (omitted from in the following expressions), and $\theta$ represent hyperparameters.

This is done via a Gaussian approximation to the posterior $q(f|y, \theta)\approx p(f|y, \theta)$, which is computed by the underlying CInferenceMethod instance (if implemented, otherwise error), and then using an importance sample estimator

\[ p(y|\theta)=\int p(y|f)p(f|\theta)df =\int p(y|f)\frac{p(f|\theta)}{q(f|y, \theta)}q(f|y, \theta)df \approx\frac{1}{n}\sum_{i=1}^n p(y|f^{(i)})\frac{p(f^{(i)}|\theta)} {q(f^{(i)}|y, \theta)}, \]

where $ f^{(i)} $ are samples from the posterior approximation $ q(f|y, \theta) $. The resulting estimator has a low variance if $ q(f|y, \theta) $ is a good approximation. It has large variance otherwise (while still being consistent). Storing all number of log-domain ensures numerical stability.

参数

num_importance_samples	the number of importance samples $n$ from $ q(f\|y, \theta) $.
ridge_size	scalar that is added to the diagonal of the involved Gaussian distribution's covariance of GP prior and posterior approximation to stabilise things. Increase if covariance matrix is not numerically positive semi-definite.

返回: unbiased estimate of the marginal likelihood function $ p(y|\theta),$ in log-domain.

在文件 InferenceMethod.cpp 第 126 行定义.

virtual CMeanFunction* get_mean ( )

virtual

get mean

返回: mean

在文件 InferenceMethod.h 第 300 行定义.

CLikelihoodModel* get_model ( )

get likelihood model

返回: likelihood

在文件 InferenceMethod.h 第 334 行定义.

SGStringList< char > get_modelsel_names ( )

inherited

返回: vector of names of all parameters which are registered for model selection

在文件 SGObject.cpp 第 498 行定义.

char * get_modsel_param_descr ( const char * param_name )

inherited

Returns description of a given parameter string, if it exists. SG_ERROR otherwise

参数

param_name name of the parameter

返回: description of the parameter

在文件 SGObject.cpp 第 522 行定义.

index_t get_modsel_param_index ( const char * param_name )

inherited

Returns index of model selection parameter with provided index

参数

param_name name of model selection parameter

返回: index of model selection parameter with provided name, -1 if there is no such

在文件 SGObject.cpp 第 535 行定义.

SGMatrix< float64_t > get_multiclass_E ( )

virtual

get the E matrix used for multi classification

返回: the matrix for multi classification

在文件 InferenceMethod.cpp 第 72 行定义.

virtual const char* get_name ( ) const

pure virtualinherited

Returns the name of the SGSerializable instance. It MUST BE the CLASS NAME without the prefixed `C'.

返回: name of the SGSerializable

virtual float64_t get_negative_log_marginal_likelihood ( )

pure virtual

get negative log marginal likelihood

返回: the negative log of the marginal likelihood function:

\[ -log(p(y|X, \theta)) \]

where $y$ are the labels, $X$ are the features, and $\theta$ represent hyperparameters.

在 CSingleFITCLaplacianInferenceMethod, CMultiLaplacianInferenceMethod, CKLInferenceMethod, CExactInferenceMethod, CFITCInferenceMethod, CSparseVGInferenceMethod, CEPInferenceMethod , 以及 CSingleLaplacianInferenceMethod 内被实现.

CMap< TParameter *, SGVector< float64_t > > * get_negative_log_marginal_likelihood_derivatives ( CMap< TParameter *, CSGObject * > * parameters )

virtual

get log marginal likelihood gradient

返回: vector of the marginal likelihood function gradient with respect to hyperparameters (under the current approximation to the posterior $q(f|y)\approx p(f|y)$:

\[ -\frac{\partial log(p(y|X, \theta))}{\partial \theta} \]

where $y$ are the labels, $X$ are the features, and $\theta$ represent hyperparameters.

在文件 InferenceMethod.cpp 第 185 行定义.

virtual SGMatrix<float64_t> get_posterior_covariance ( )

pure virtual

returns covariance matrix $\Sigma$ of the Gaussian distribution $\mathcal{N}(\mu,\Sigma)$, which is an approximation to the posterior:

\[ p(f|y) \approx q(f|y) = \mathcal{N}(\mu,\Sigma) \]

in case if particular inference method doesn't compute posterior $p(f|y)$ exactly, and it returns covariance matrix $\Sigma$ of the posterior Gaussian distribution $\mathcal{N}(\mu,\Sigma)$ otherwise.

返回: covariance matrix

在 CSparseInferenceBase, CEPInferenceMethod, CExactInferenceMethod, CFITCInferenceMethod, CSparseVGInferenceMethod, CSingleFITCLaplacianInferenceMethod, CKLInferenceMethod , 以及 CLaplacianInferenceBase 内被实现.

virtual SGVector<float64_t> get_posterior_mean ( )

pure virtual

get alpha vector

返回: vector to compute posterior mean of Gaussian Process:

\[ \mu = K\alpha+meanf \]

where $\mu$ is the mean, $K$ is the prior covariance matrix, and $meanf$\f is the mean prior fomr MeanFunction */ virtual SGVector<float64_t> get_alpha()=0; /** get Cholesky decomposition matrix @return Cholesky decomposition of matrix */ virtual SGMatrix<float64_t> get_cholesky()=0; /** get diagonal vector @return diagonal of matrix used to calculate posterior covariance matrix */ virtual SGVector<float64_t> get_diagonal_vector()=0; /** returns mean vector $$ of the Gaussian distribution $\mathcal{N}(\mu,\Sigma)$, which is an approximation to the posterior:

\[ p(f|y) \approx q(f|y) = \mathcal{N}(\mu,\Sigma) \]

in case if particular inference method doesn't compute posterior $p(f|y)$ exactly, and it returns covariance matrix $\Sigma$ of the posterior Gaussian distribution $\mathcal{N}(\mu,\Sigma)$ otherwise.

返回: mean vector

在 CSparseInferenceBase, CEPInferenceMethod, CExactInferenceMethod, CMultiLaplacianInferenceMethod, CFITCInferenceMethod, CSparseVGInferenceMethod, CSingleFITCLaplacianInferenceMethod, CSingleLaplacianInferenceMethod , 以及 CKLInferenceMethod 内被实现.

float64_t get_scale ( ) const

virtual

get kernel scale

返回: kernel scale

在文件 InferenceMethod.cpp 第 61 行定义.

virtual SGVector<float64_t> get_value ( )

virtual

get the function value

返回: vector that represents the function value

实现了 CDifferentiableFunction.

在文件 InferenceMethod.h 第 255 行定义.

bool is_generic ( EPrimitiveType * generic ) const

virtualinherited

If the SGSerializable is a class template then TRUE will be returned and GENERIC is set to the type of the generic.

参数

generic set to the type of the generic if returning TRUE

返回: TRUE if a class template.

在文件 SGObject.cpp 第 296 行定义.

bool load_serializable	(	CSerializableFile *	file,
		const char *	prefix = `""`
	)

virtualinherited

Load this object from file. If it will fail (returning FALSE) then this object will contain inconsistent data and should not be used!

参数

file	where to load from
prefix	prefix for members

返回: TRUE if done, otherwise FALSE

在文件 SGObject.cpp 第 369 行定义.

void load_serializable_post	(		)
throw	(	ShogunException
	)

protectedvirtualinherited

Can (optionally) be overridden to post-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::LOAD_SERIALIZABLE_POST is called.

异常

ShogunException will be thrown if an error occurs.

被 CKernel, CWeightedDegreePositionStringKernel, CList, CAlphabet, CLinearHMM, CGaussianKernel, CInverseMultiQuadricKernel, CCircularKernel , 以及 CExponentialKernel 重载.

在文件 SGObject.cpp 第 426 行定义.

void load_serializable_pre	(		)
throw	(	ShogunException
	)

protectedvirtualinherited

Can (optionally) be overridden to pre-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::LOAD_SERIALIZABLE_PRE is called.

异常

ShogunException will be thrown if an error occurs.

被 CDynamicArray< T >, CDynamicArray< float64_t >, CDynamicArray< float32_t >, CDynamicArray< int32_t >, CDynamicArray< char >, CDynamicArray< bool > , 以及 CDynamicObjectArray 重载.

在文件 SGObject.cpp 第 421 行定义.

bool parameter_hash_changed ( )

virtualinherited

返回: whether parameter combination has changed since last update

在文件 SGObject.cpp 第 262 行定义.

void print_modsel_params ( )

inherited

prints all parameter registered for model selection and their type

在文件 SGObject.cpp 第 474 行定义.

void print_serializable ( const char * prefix = "" )

virtualinherited

prints registered parameters out

参数

prefix prefix for members

在文件 SGObject.cpp 第 308 行定义.

bool save_serializable	(	CSerializableFile *	file,
		const char *	prefix = `""`
	)

virtualinherited

Save this object to file.

参数

file	where to save the object; will be closed during returning if PREFIX is an empty string.
prefix	prefix for members

返回: TRUE if done, otherwise FALSE

在文件 SGObject.cpp 第 314 行定义.

void save_serializable_post	(		)
throw	(	ShogunException
	)

protectedvirtualinherited

Can (optionally) be overridden to post-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::SAVE_SERIALIZABLE_POST is called.

异常

ShogunException will be thrown if an error occurs.

被 CKernel 重载.

在文件 SGObject.cpp 第 436 行定义.

void save_serializable_pre	(		)
throw	(	ShogunException
	)

protectedvirtualinherited

Can (optionally) be overridden to pre-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::SAVE_SERIALIZABLE_PRE is called.

异常

ShogunException will be thrown if an error occurs.

被 CKernel, CDynamicArray< T >, CDynamicArray< float64_t >, CDynamicArray< float32_t >, CDynamicArray< int32_t >, CDynamicArray< char >, CDynamicArray< bool > , 以及 CDynamicObjectArray 重载.

在文件 SGObject.cpp 第 431 行定义.

virtual void set_features ( CFeatures * feat )

virtual

set features

参数

feat	features to set

在文件 InferenceMethod.h 第 272 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 41 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 46 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 51 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 56 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 61 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 66 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 71 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 76 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 81 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 86 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 91 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 96 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 101 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 106 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 111 行定义.

void set_generic ( )

inherited

set generic type to T

void set_global_io ( SGIO * io )

inherited

set the io object

参数

io	io object to use

在文件 SGObject.cpp 第 228 行定义.

void set_global_parallel ( Parallel * parallel )

inherited

set the parallel object

参数

parallel parallel object to use

在文件 SGObject.cpp 第 241 行定义.

void set_global_version ( Version * version )

inherited

set the version object

参数

version version object to use

在文件 SGObject.cpp 第 283 行定义.

virtual void set_kernel ( CKernel * kern )

virtual

set kernel

参数

kern	kernel to set

被 CSingleSparseInferenceBase 重载.

在文件 InferenceMethod.h 第 289 行定义.

virtual void set_labels ( CLabels * lab )

virtual

set labels

参数

lab	label to set

在文件 InferenceMethod.h 第 323 行定义.

virtual void set_mean ( CMeanFunction * m )

virtual

set mean

参数

m	mean function to set

在文件 InferenceMethod.h 第 306 行定义.

virtual void set_model ( CLikelihoodModel * mod )

virtual

set likelihood model

参数

mod	model to set

被 CKLInferenceMethod , 以及 CKLDualInferenceMethod 重载.

在文件 InferenceMethod.h 第 340 行定义.

void set_scale ( float64_t scale )

virtual

set kernel scale

参数

scale scale to be set

在文件 InferenceMethod.cpp 第 66 行定义.

CSGObject * shallow_copy ( ) const

virtualinherited

A shallow copy. All the SGObject instance variables will be simply assigned and SG_REF-ed.

被 CGaussianKernel 重载.

在文件 SGObject.cpp 第 192 行定义.

virtual bool supports_binary ( ) const

virtual

whether combination of inference method and given likelihood function supports binary classification

返回: false

被 CEPInferenceMethod, CKLInferenceMethod, CSingleFITCLaplacianInferenceMethod , 以及 CSingleLaplacianInferenceMethod 重载.

在文件 InferenceMethod.h 第 371 行定义.

virtual bool supports_multiclass ( ) const

virtual

whether combination of inference method and given likelihood function supports multiclass classification

返回: false

在文件 InferenceMethod.h 第 378 行定义.

virtual bool supports_regression ( ) const

virtual

whether combination of inference method and given likelihood function supports regression

返回: false

被 CExactInferenceMethod, CKLInferenceMethod, CFITCInferenceMethod, CSparseVGInferenceMethod, CSingleFITCLaplacianInferenceMethod , 以及 CSingleLaplacianInferenceMethod 重载.

在文件 InferenceMethod.h 第 364 行定义.

void unset_generic ( )

inherited

unset generic type

this has to be called in classes specializing a template class

在文件 SGObject.cpp 第 303 行定义.

void update ( )

virtual

update matrices except gradients

被 CEPInferenceMethod, CSingleFITCLaplacianInferenceMethod, CExactInferenceMethod, CKLInferenceMethod, CFITCInferenceMethod, CSparseVGInferenceMethod, CSparseInferenceBase, CLaplacianInferenceBase , 以及 CSingleLaplacianInferenceMethod 重载.

在文件 InferenceMethod.cpp 第 303 行定义.

virtual void update_alpha ( )

protectedpure virtual

update alpha vector

在 CEPInferenceMethod, CSingleFITCLaplacianInferenceMethod, CExactInferenceMethod, CSingleFITCLaplacianBase, CFITCInferenceMethod, CSparseVGInferenceMethod, CMultiLaplacianInferenceMethod, CKLDualInferenceMethod, CSingleLaplacianInferenceMethodWithLBFGS, CSingleFITCLaplacianInferenceMethodWithLBFGS, CSingleLaplacianInferenceMethod, CKLCovarianceInferenceMethod, CKLApproxDiagonalInferenceMethod , 以及 CKLCholeskyInferenceMethod 内被实现.

virtual void update_chol ( )

protectedpure virtual

update cholesky matrix

在 CEPInferenceMethod, CSingleFITCLaplacianInferenceMethod, CExactInferenceMethod, CSingleFITCLaplacianBase, CFITCInferenceMethod, CSparseVGInferenceMethod, CMultiLaplacianInferenceMethod, CKLDualInferenceMethod, CSingleLaplacianInferenceMethod, CKLCovarianceInferenceMethod , 以及 CKLLowerTriangularInferenceMethod 内被实现.

virtual void update_deriv ( )

protectedpure virtual

update matrices which are required to compute negative log marginal likelihood derivatives wrt hyperparameter

在 CEPInferenceMethod, CSingleFITCLaplacianInferenceMethod, CExactInferenceMethod, CSingleFITCLaplacianBase, CFITCInferenceMethod, CSparseVGInferenceMethod, CMultiLaplacianInferenceMethod, CKLDualInferenceMethod, CSingleLaplacianInferenceMethod, CKLCovarianceInferenceMethod , 以及 CKLLowerTriangularInferenceMethod 内被实现.

void update_parameter_hash ( )

virtualinherited

Updates the hash of current parameter combination

在文件 SGObject.cpp 第 248 行定义.

void update_train_kernel ( )

protectedvirtual

update train kernel matrix

被 CSparseInferenceBase 重载.

在文件 InferenceMethod.cpp 第 324 行定义.

类成员变量说明

SGIO* io

inherited

io

在文件 SGObject.h 第 369 行定义.

SGVector<float64_t> m_alpha

protected

alpha vector used in process mean calculation

在文件 InferenceMethod.h 第 475 行定义.

SGMatrix<float64_t> m_E

protected

the matrix used for multi classification

在文件 InferenceMethod.h 第 487 行定义.

CFeatures* m_features

protected

features to use

在文件 InferenceMethod.h 第 469 行定义.

Parameter* m_gradient_parameters

inherited

parameters wrt which we can compute gradients

在文件 SGObject.h 第 384 行定义.

bool m_gradient_update

protected

Whether gradients are updated

在文件 InferenceMethod.h 第 490 行定义.

uint32_t m_hash

inherited

Hash of parameter values

在文件 SGObject.h 第 387 行定义.

CKernel* m_kernel

protected

covariance function

在文件 InferenceMethod.h 第 460 行定义.

SGMatrix<float64_t> m_ktrtr

protected

kernel matrix from features (non-scalled by inference scalling)

在文件 InferenceMethod.h 第 484 行定义.

SGMatrix<float64_t> m_L

protected

upper triangular factor of Cholesky decomposition

在文件 InferenceMethod.h 第 478 行定义.

CLabels* m_labels

protected

labels of features

在文件 InferenceMethod.h 第 472 行定义.

float64_t m_log_scale

protected

kernel scale

在文件 InferenceMethod.h 第 481 行定义.

CMeanFunction* m_mean

protected

mean function

在文件 InferenceMethod.h 第 463 行定义.

CLikelihoodModel* m_model

protected

likelihood function to use

在文件 InferenceMethod.h 第 466 行定义.

Parameter* m_model_selection_parameters

inherited

model selection parameters

在文件 SGObject.h 第 381 行定义.

Parameter* m_parameters

inherited

parameters

在文件 SGObject.h 第 378 行定义.

Parallel* parallel

inherited

parallel

在文件 SGObject.h 第 372 行定义.

Version* version

inherited

version

在文件 SGObject.h 第 375 行定义.

该类的文档由以下文件生成:

num_importance_samples	the number of importance samples \(n\) from \( q(f\|y, \theta) \).
ridge_size	scalar that is added to the diagonal of the involved Gaussian distribution's covariance of GP prior and posterior approximation to stabilise things. Increase if covariance matrix is not numerically positive semi-definite.

详细描述

Public 成员函数

Public 属性

Protected 成员函数

静态 Protected 成员函数

Protected 属性

构造及析构函数说明

成员函数说明

类成员变量说明