SHOGUN  4.1.0
 全部  命名空间 文件 函数 变量 类型定义 枚举 枚举值 友元 宏定义  
所有成员列表 | Public 成员函数 | Public 属性 | Protected 成员函数 | Protected 属性
CDualVariationalGaussianLikelihood类 参考abstract

详细描述

Class that models dual variational likelihood.

This likelihood model is described in the reference paper Mohammad Emtiyaz Khan, Aleksandr Y. Aravkin, Michael P. Friedlander, Matthias Seeger Fast Dual Variational Inference for Non-Conjugate Latent Gaussian Models. ICML2013

The mathematical definition (equation 19 in the paper) is as below

\[ Fenchel_i(\alpha_i,\lambda_i) = max_{h_i,\rho_i}{\alpha_i h_i+\lambda_i \rho_i /2 - E_{q(f_i|h_i,\rho_i)}(-log(p(y_i|f_i)))} \]

where \(\alpha_i\), \(\lambda_i\) are Lagrange multipliers with respective to constraints \(h_i=\mu_i\) and \(\rho_i=\sigma_i^2\) respectively, \(\mu\) and \(\sigma_i\) are variational Gaussian parameters, y_i is data label, \(q(f_i)\) is the variational Gaussian distribution, and p(y_i) is the data distribution to be specified. In this setting, \(\alpha\) and \(\lambda\) are called dual parameters for \(\mu\) and \(\sigma^2\) respectively.

在文件 DualVariationalGaussianLikelihood.h63 行定义.

类 CDualVariationalGaussianLikelihood 继承关系图:
Inheritance graph
[图例]

Public 成员函数

 CDualVariationalGaussianLikelihood ()
 
virtual ~CDualVariationalGaussianLikelihood ()
 
virtual const char * get_name () const
 
virtual SGVector< float64_tget_variational_expection ()
 
virtual SGVector< float64_tget_variational_first_derivative (const TParameter *param) const
 
virtual bool supports_derivative_wrt_hyperparameter () const
 
virtual SGVector< float64_tget_first_derivative_wrt_hyperparameter (const TParameter *param) const
 
virtual bool set_variational_distribution (SGVector< float64_t > mu, SGVector< float64_t > s2, const CLabels *lab)
 
virtual bool dual_parameters_valid () const
 
virtual float64_t adjust_step_wrt_dual_parameter (SGVector< float64_t > direction, const float64_t step) const
 
virtual void set_dual_parameters (SGVector< float64_t > the_lambda, const CLabels *lab)
 
virtual SGVector< float64_tget_mu_dual_parameter () const =0
 
virtual SGVector< float64_tget_variance_dual_parameter () const =0
 
virtual float64_t get_dual_upper_bound () const =0
 
virtual float64_t get_dual_lower_bound () const =0
 
virtual bool dual_upper_bound_strict () const =0
 
virtual bool dual_lower_bound_strict () const =0
 
virtual SGVector< float64_tget_dual_objective_value ()=0
 
virtual SGVector< float64_tget_dual_first_derivative (const TParameter *param) const =0
 
virtual void set_strict_scale (float64_t strict_scale)
 
virtual void set_noise_factor (float64_t noise_factor)
 
virtual SGVector< float64_tget_predictive_means (SGVector< float64_t > mu, SGVector< float64_t > s2, const CLabels *lab=NULL) const
 
virtual SGVector< float64_tget_predictive_variances (SGVector< float64_t > mu, SGVector< float64_t > s2, const CLabels *lab=NULL) const
 
virtual ELikelihoodModelType get_model_type () const
 
virtual SGVector< float64_tget_log_probability_f (const CLabels *lab, SGVector< float64_t > func) const
 
virtual SGVector< float64_tget_log_probability_derivative_f (const CLabels *lab, SGVector< float64_t > func, index_t i) const
 
virtual SGVector< float64_tget_log_zeroth_moments (SGVector< float64_t > mu, SGVector< float64_t > s2, const CLabels *lab) const
 
virtual float64_t get_first_moment (SGVector< float64_t > mu, SGVector< float64_t > s2, const CLabels *lab, index_t i) const
 
virtual float64_t get_second_moment (SGVector< float64_t > mu, SGVector< float64_t > s2, const CLabels *lab, index_t i) const
 
virtual bool supports_regression () const
 
virtual bool supports_binary () const
 
virtual bool supports_multiclass () const
 
virtual SGVector< float64_tget_first_derivative (const CLabels *lab, SGVector< float64_t > func, const TParameter *param) const
 
virtual SGVector< float64_tget_second_derivative (const CLabels *lab, SGVector< float64_t > func, const TParameter *param) const
 
virtual SGVector< float64_tget_third_derivative (const CLabels *lab, SGVector< float64_t > func, const TParameter *param) const
 
virtual SGVector< float64_tget_predictive_log_probabilities (SGVector< float64_t > mu, SGVector< float64_t > s2, const CLabels *lab=NULL)
 
virtual SGVector< float64_tget_log_probability_fmatrix (const CLabels *lab, SGMatrix< float64_t > F) const
 
virtual SGVector< float64_tget_first_moments (SGVector< float64_t > mu, SGVector< float64_t > s2, const CLabels *lab) const
 
virtual SGVector< float64_tget_second_moments (SGVector< float64_t > mu, SGVector< float64_t > s2, const CLabels *lab) const
 
virtual CSGObjectshallow_copy () const
 
virtual CSGObjectdeep_copy () const
 
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)
 
SGIOget_global_io ()
 
void set_global_parallel (Parallel *parallel)
 
Parallelget_global_parallel ()
 
void set_global_version (Version *version)
 
Versionget_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 CSGObjectclone ()
 

Public 属性

SGIOio
 
Parallelparallel
 
Versionversion
 
Parameterm_parameters
 
Parameterm_model_selection_parameters
 
Parameterm_gradient_parameters
 
uint32_t m_hash
 

Protected 成员函数

virtual void precompute ()
 
virtual
CVariationalGaussianLikelihood
get_variational_likelihood () const
 
virtual void init_likelihood ()=0
 
virtual void set_likelihood (CLikelihoodModel *lik)
 
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)
 

Protected 属性

SGVector< float64_tm_lambda
 
float64_t m_strict_scale
 
bool m_is_valid
 
SGVector< float64_tm_mu
 
SGVector< float64_tm_s2
 
SGVector< float64_tm_lab
 
CLikelihoodModelm_likelihood
 

构造及析构函数说明

default constructor

在文件 DualVariationalGaussianLikelihood.cpp45 行定义.

在文件 DualVariationalGaussianLikelihood.cpp51 行定义.

成员函数说明

float64_t adjust_step_wrt_dual_parameter ( SGVector< float64_t direction,
const float64_t  step 
) const
virtual

this method is used for adjusting step size to ensure the updated value satisfied lower/upper bound constrain

The updated value is defined as below. lambda_new = m_lambda + direction * step

参数
directiondirection for m_lambda update
steporiginal step size (non-negative)
返回
adjusted step size

在文件 DualVariationalGaussianLikelihood.cpp111 行定义.

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
dictdictionary of parameters to be built.

在文件 SGObject.cpp597 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.cpp714 行定义.

CSGObject * deep_copy ( ) const
virtualinherited

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

在文件 SGObject.cpp198 行定义.

virtual bool dual_lower_bound_strict ( ) const
pure virtual

whether the lower bound is strict

返回
true if the lower bound is strict

CLogitDVGLikelihood 内被实现.

bool dual_parameters_valid ( ) const
virtual

check whether the dual parameters are valid or not.

返回
true if dual parameters are valid

在文件 DualVariationalGaussianLikelihood.cpp182 行定义.

virtual bool dual_upper_bound_strict ( ) const
pure virtual

whether the upper bound is strict

返回
true if the upper bound is strict

CLogitDVGLikelihood 内被实现.

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
otherobject to compare with
accuracyaccuracy to use for comparison (optional)
tolerantallows linient check on float equality (within accuracy)
返回
true if all parameters were equal, false if not

在文件 SGObject.cpp618 行定义.

virtual SGVector<float64_t> get_dual_first_derivative ( const TParameter param) const
pure virtual

get the derivative of the dual objective function with respect to param

参数
paramparameter
返回
the value of of the derivative

CLogitDVGLikelihood 内被实现.

virtual float64_t get_dual_lower_bound ( ) const
pure virtual

get the lower bound for dual parameter (lambda)

返回
the lower bound

CLogitDVGLikelihood 内被实现.

virtual SGVector<float64_t> get_dual_objective_value ( )
pure virtual

evaluate the dual objective function

返回
the value of Fenchel conjugates given m_lambda

CLogitDVGLikelihood 内被实现.

virtual float64_t get_dual_upper_bound ( ) const
pure virtual

get the upper bound for dual parameter (lambda)

返回
the upper bound

CLogitDVGLikelihood 内被实现.

SGVector< float64_t > get_first_derivative ( const CLabels lab,
SGVector< float64_t func,
const TParameter param 
) const
virtualinherited

get derivative of log likelihood \(log(p(y|f))\) with respect to given parameter

参数
lablabels used
funcfunction location
paramparameter
返回
derivative

重载 CLikelihoodModel .

在文件 VariationalLikelihood.cpp88 行定义.

SGVector< float64_t > get_first_derivative_wrt_hyperparameter ( const TParameter param) const
virtual

get derivative of log likelihood \(log(p(y|f))\) with respect to given hyperparameter Note that variational parameters are NOT considered as hyperparameters

参数
paramparameter
返回
derivative

实现了 CVariationalLikelihood.

在文件 DualVariationalGaussianLikelihood.cpp90 行定义.

float64_t get_first_moment ( SGVector< float64_t mu,
SGVector< float64_t s2,
const CLabels lab,
index_t  i 
) const
virtualinherited

returns the first moment of a given (unnormalized) probability distribution \(q(f_i) = Z_i^-1 p(y_i|f_i)\mathcal{N}(f_i|\mu,\sigma^2)\), where \( Z_i=\int p(y_i|f_i)\mathcal{N}(f_i|\mu,\sigma^2) df_i\).

This method is useful for EP local likelihood approximation.

参数
mumean of the \(\mathcal{N}(f_i|\mu,\sigma^2)\)
s2variance of the \(\mathcal{N}(f_i|\mu,\sigma^2)\)
lablabels \(y_i\)
iindex i
返回
first moment of \(q(f_i)\)

实现了 CLikelihoodModel.

在文件 VariationalLikelihood.cpp140 行定义.

SGVector< float64_t > get_first_moments ( SGVector< float64_t mu,
SGVector< float64_t s2,
const CLabels lab 
) const
virtualinherited

returns the first moment of a given (unnormalized) probability distribution \(q(f_i) = Z_i^-1 p(y_i|f_i)\mathcal{N}(f_i|\mu,\sigma^2)\) for each \(f_i\), where \( Z_i=\int p(y_i|f_i)\mathcal{N}(f_i|\mu,\sigma^2) df_i\).

Wrapper method which calls get_first_moment multiple times.

参数
mumean of the \(\mathcal{N}(f_i|\mu,\sigma^2)\)
s2variance of the \(\mathcal{N}(f_i|\mu,\sigma^2)\)
lablabels \(y_i\)
返回
the first moment of \(q(f_i)\) for each \(f_i\)

在文件 LikelihoodModel.cpp72 行定义.

SGIO * get_global_io ( )
inherited

get the io object

返回
io object

在文件 SGObject.cpp235 行定义.

Parallel * get_global_parallel ( )
inherited

get the parallel object

返回
parallel object

在文件 SGObject.cpp277 行定义.

Version * get_global_version ( )
inherited

get the version object

返回
version object

在文件 SGObject.cpp290 行定义.

SGVector< float64_t > get_log_probability_derivative_f ( const CLabels lab,
SGVector< float64_t func,
index_t  i 
) const
virtualinherited

get derivative of log likelihood \(log(p(y|f))\) with respect to location function \(f\)

参数
lablabels used
funcfunction location
iindex, choices are 1, 2, and 3 for first, second, and third derivatives respectively
返回
derivative

实现了 CLikelihoodModel.

在文件 VariationalLikelihood.cpp125 行定义.

SGVector< float64_t > get_log_probability_f ( const CLabels lab,
SGVector< float64_t func 
) const
virtualinherited

Returns the logarithm of the point-wise likelihood \(log(p(y_i|f_i))\) for each label \(y_i\).

One can evaluate log-likelihood like: \( log(p(y|f)) = \sum_{i=1}^{n} log(p(y_i|f_i))\)

参数
lablabels \(y_i\)
funcvalues of the function \(f_i\)
返回
logarithm of the point-wise likelihood

实现了 CLikelihoodModel.

在文件 VariationalLikelihood.cpp118 行定义.

SGVector< float64_t > get_log_probability_fmatrix ( const CLabels lab,
SGMatrix< float64_t F 
) const
virtualinherited

Returns the log-likelihood \(log(p(y|f)) = \sum_{i=1}^{n} log(p(y_i|f_i))\) for each of the provided functions \( f \) in the given matrix.

Wrapper method which calls get_log_probability_f multiple times.

参数
lablabels \(y_i\)
Fvalues of the function \(f_i\) where each column of the matrix is one function \( f \).
返回
log-likelihood for every provided function

在文件 LikelihoodModel.cpp51 行定义.

SGVector< float64_t > get_log_zeroth_moments ( SGVector< float64_t mu,
SGVector< float64_t s2,
const CLabels lab 
) const
virtualinherited

returns the zeroth moment of a given (unnormalized) probability distribution:

\[ log(Z_i) = log\left(\int p(y_i|f_i) \mathcal{N}(f_i|\mu,\sigma^2) df_i\right) \]

for each \(f_i\).

参数
mumean of the \(\mathcal{N}(f_i|\mu,\sigma^2)\)
s2variance of the \(\mathcal{N}(f_i|\mu,\sigma^2)\)
lablabels \(y_i\)
返回
log zeroth moment \(log(Z_i)\)

实现了 CLikelihoodModel.

在文件 VariationalLikelihood.cpp132 行定义.

ELikelihoodModelType get_model_type ( ) const
virtualinherited

get model type

返回
model type NONE

重载 CLikelihoodModel .

在文件 VariationalLikelihood.cpp112 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.cpp498 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_namename of the parameter
返回
description of the parameter

在文件 SGObject.cpp522 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_namename of model selection parameter
返回
index of model selection parameter with provided name, -1 if there is no such

在文件 SGObject.cpp535 行定义.

virtual SGVector<float64_t> get_mu_dual_parameter ( ) const
pure virtual

get the dual parameter (alpha) for variational mu

返回
the dual parameter (alpha)

CLogitDVGLikelihood 内被实现.

virtual const char* get_name ( ) const
virtual

returns the name of the likelihood model

返回
name DualVariationalGaussianLikelihood

实现了 CSGObject.

CLogitDVGLikelihood 重载.

在文件 DualVariationalGaussianLikelihood.h75 行定义.

SGVector< float64_t > get_predictive_log_probabilities ( SGVector< float64_t mu,
SGVector< float64_t s2,
const CLabels lab = NULL 
)
virtualinherited

returns the logarithm of the predictive density of \(y_*\):

\[ log(p(y_*|X,y,x_*)) = log\left(\int p(y_*|f_*) p(f_*|X,y,x_*) df_*\right) \]

which approximately equals to

\[ log\left(\int p(y_*|f_*) \mathcal{N}(f_*|\mu,\sigma^2) df_*\right) \]

where normal distribution \(\mathcal{N}(\mu,\sigma^2)\) is an approximation to the posterior marginal \(p(f_*|X,y,x_*)\).

NOTE: if lab equals to NULL, then each \(y_*\) equals to one.

参数
muposterior mean of a Gaussian distribution \(\mathcal{N}(\mu,\sigma^2)\), which is an approximation to the posterior marginal \(p(f_*|X,y,x_*)\)
s2posterior variance of a Gaussian distribution \(\mathcal{N}(\mu,\sigma^2)\), which is an approximation to the posterior marginal \(p(f_*|X,y,x_*)\)
lablabels \(y_*\)
返回
\(log(p(y_*|X, y, x*))\) for each label \(y_*\)

CSoftMaxLikelihood 重载.

在文件 LikelihoodModel.cpp45 行定义.

SGVector< float64_t > get_predictive_means ( SGVector< float64_t mu,
SGVector< float64_t s2,
const CLabels lab = NULL 
) const
virtualinherited

returns mean of the predictive marginal \(p(y_*|X,y,x_*)\)

NOTE: if lab equals to NULL, then each \(y_*\) equals to one.

参数
muposterior mean of a Gaussian distribution \(\mathcal{N}(\mu,\sigma^2)\), which is an approximation to the posterior marginal \(p(f_*|X,y,x_*)\)
s2posterior variance of a Gaussian distribution \(\mathcal{N}(\mu,\sigma^2)\), which is an approximation to the posterior marginal \(p(f_*|X,y,x_*)\)
lablabels \(y_*\)
返回
final means evaluated by likelihood function

实现了 CLikelihoodModel.

在文件 VariationalLikelihood.cpp72 行定义.

SGVector< float64_t > get_predictive_variances ( SGVector< float64_t mu,
SGVector< float64_t s2,
const CLabels lab = NULL 
) const
virtualinherited

returns variance of the predictive marginal \(p(y_*|X,y,x_*)\)

NOTE: if lab equals to NULL, then each \(y_*\) equals to one.

参数
muposterior mean of a Gaussian distribution \(\mathcal{N}(\mu,\sigma^2)\), which is an approximation to the posterior marginal \(p(f_*|X,y,x_*)\)
s2posterior variance of a Gaussian distribution \(\mathcal{N}(\mu,\sigma^2)\), which is an approximation to the posterior marginal \(p(f_*|X,y,x_*)\)
lablabels \(y_*\)
返回
final variances evaluated by likelihood function

实现了 CLikelihoodModel.

在文件 VariationalLikelihood.cpp80 行定义.

SGVector< float64_t > get_second_derivative ( const CLabels lab,
SGVector< float64_t func,
const TParameter param 
) const
virtualinherited

get derivative of the first derivative of log likelihood with respect to function location, i.e. \(\frac{\partial log(p(y|f))}{\partial f}\) with respect to given parameter

参数
lablabels used
funcfunction location
paramparameter
返回
derivative

重载 CLikelihoodModel .

在文件 VariationalLikelihood.cpp96 行定义.

float64_t get_second_moment ( SGVector< float64_t mu,
SGVector< float64_t s2,
const CLabels lab,
index_t  i 
) const
virtualinherited

returns the second moment of a given (unnormalized) probability distribution \(q(f_i) = Z_i^-1 p(y_i|f_i)\mathcal{N}(f_i|\mu,\sigma^2)\), where \( Z_i=\int p(y_i|f_i)\mathcal{N}(f_i|\mu,\sigma^2) df_i\).

This method is useful for EP local likelihood approximation.

参数
mumean of the \(\mathcal{N}(f_i|\mu,\sigma^2)\)
s2variance of the \(\mathcal{N}(f_i|\mu,\sigma^2)\)
lablabels \(y_i\)
iindex i
返回
the second moment of \(q(f_i)\)

实现了 CLikelihoodModel.

在文件 VariationalLikelihood.cpp148 行定义.

SGVector< float64_t > get_second_moments ( SGVector< float64_t mu,
SGVector< float64_t s2,
const CLabels lab 
) const
virtualinherited

returns the second moment of a given (unnormalized) probability distribution \(q(f_i) = Z_i^-1 p(y_i|f_i)\mathcal{N}(f_i|\mu,\sigma^2)\) for each \(f_i\), where \( Z_i=\int p(y_i|f_i)\mathcal{N}(f_i|\mu,\sigma^2) df_i\).

Wrapper method which calls get_second_moment multiple times.

参数
mumean of the \(\mathcal{N}(f_i|\mu,\sigma^2)\)
s2variance of the \(\mathcal{N}(f_i|\mu,\sigma^2)\)
lablabels \(y_i\)
返回
the second moment of \(q(f_i)\) for each \(f_i\)

在文件 LikelihoodModel.cpp89 行定义.

SGVector< float64_t > get_third_derivative ( const CLabels lab,
SGVector< float64_t func,
const TParameter param 
) const
virtualinherited

get derivative of the second derivative of log likelihood with respect to function location, i.e. \(\frac{\partial^{2} log(p(y|f))}{\partial f^{2}}\) with respect to given parameter

参数
lablabels used
funcfunction location
paramparameter
返回
derivative

重载 CLikelihoodModel .

在文件 VariationalLikelihood.cpp104 行定义.

virtual SGVector<float64_t> get_variance_dual_parameter ( ) const
pure virtual

get the dual parameter (lambda) for variational s2

返回
the dual parameter (lambda)

CLogitDVGLikelihood 内被实现.

SGVector< float64_t > get_variational_expection ( )
virtual

returns the expection of the logarithm of a given probability distribution wrt the variational distribution given m_mu and m_s2

返回
expection

实现了 CVariationalLikelihood.

在文件 DualVariationalGaussianLikelihood.cpp66 行定义.

SGVector< float64_t > get_variational_first_derivative ( const TParameter param) const
virtual

get derivative of the variational expection of log likelihood with respect to given parameter

参数
paramparameter
返回
derivative

实现了 CVariationalLikelihood.

在文件 DualVariationalGaussianLikelihood.cpp78 行定义.

CVariationalGaussianLikelihood * get_variational_likelihood ( ) const
protectedvirtual

this method is used to dynamic-cast the likelihood model, m_likelihood, to variational likelihood model.

在文件 DualVariationalGaussianLikelihood.cpp55 行定义.

virtual void init_likelihood ( )
protectedpure virtualinherited

this method is called to initialize m_likelihood in init()

实现了 CVariationalLikelihood.

CLogitDVGLikelihood, CLogitVGPiecewiseBoundLikelihood, CNumericalVGLikelihood, CLogitVGLikelihood, CProbitVGLikelihood , 以及 CStudentsTVGLikelihood 内被实现.

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
genericset to the type of the generic if returning TRUE
返回
TRUE if a class template.

在文件 SGObject.cpp296 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
filewhere to load from
prefixprefix for members
返回
TRUE if done, otherwise FALSE

在文件 SGObject.cpp369 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
ShogunExceptionwill be thrown if an error occurs.

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

在文件 SGObject.cpp426 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
ShogunExceptionwill be thrown if an error occurs.

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

在文件 SGObject.cpp421 行定义.

bool parameter_hash_changed ( )
virtualinherited
返回
whether parameter combination has changed since last update

在文件 SGObject.cpp262 行定义.

void precompute ( )
protectedvirtual

compute common variables later used in get_variational_expection and get_variational_first_derivative. Note that this method will automatically be called when set_variational_distribution is called

在文件 DualVariationalGaussianLikelihood.cpp213 行定义.

void print_modsel_params ( )
inherited

prints all parameter registered for model selection and their type

在文件 SGObject.cpp474 行定义.

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

prints registered parameters out

参数
prefixprefix for members

在文件 SGObject.cpp308 行定义.

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

Save this object to file.

参数
filewhere to save the object; will be closed during returning if PREFIX is an empty string.
prefixprefix for members
返回
TRUE if done, otherwise FALSE

在文件 SGObject.cpp314 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
ShogunExceptionwill be thrown if an error occurs.

CKernel 重载.

在文件 SGObject.cpp436 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
ShogunExceptionwill be thrown if an error occurs.

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.cpp431 行定义.

void set_dual_parameters ( SGVector< float64_t the_lambda,
const CLabels lab 
)
virtual

set dual parameters for variational parameters

参数
the_lambdadual parameter for variational mean
lablabels/data used

Note that dual parameter (alpha) for the variational variance is implicitly set based on lambda

在文件 DualVariationalGaussianLikelihood.cpp157 行定义.

void set_generic ( )
inherited

在文件 SGObject.cpp41 行定义.

void set_generic ( )
inherited

在文件 SGObject.cpp46 行定义.

void set_generic ( )
inherited

在文件 SGObject.cpp51 行定义.

void set_generic ( )
inherited

在文件 SGObject.cpp56 行定义.

void set_generic ( )
inherited

在文件 SGObject.cpp61 行定义.

void set_generic ( )
inherited

在文件 SGObject.cpp66 行定义.

void set_generic ( )
inherited

在文件 SGObject.cpp71 行定义.

void set_generic ( )
inherited

在文件 SGObject.cpp76 行定义.

void set_generic ( )
inherited

在文件 SGObject.cpp81 行定义.

void set_generic ( )
inherited

在文件 SGObject.cpp86 行定义.

void set_generic ( )
inherited

在文件 SGObject.cpp91 行定义.

void set_generic ( )
inherited

在文件 SGObject.cpp96 行定义.

void set_generic ( )
inherited

在文件 SGObject.cpp101 行定义.

void set_generic ( )
inherited

在文件 SGObject.cpp106 行定义.

void set_generic ( )
inherited

在文件 SGObject.cpp111 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
ioio object to use

在文件 SGObject.cpp228 行定义.

void set_global_parallel ( Parallel parallel)
inherited

set the parallel object

参数
parallelparallel object to use

在文件 SGObject.cpp241 行定义.

void set_global_version ( Version version)
inherited

set the version object

参数
versionversion object to use

在文件 SGObject.cpp283 行定义.

void set_likelihood ( CLikelihoodModel lik)
protectedvirtualinherited

this method used to set m_likelihood

在文件 VariationalLikelihood.cpp49 行定义.

void set_noise_factor ( float64_t  noise_factor)
virtual

set a non-negative noise factor in order to correct the variance if variance is close to zero or negative setting 0 means correction is not applied

参数
noise_factornoise factor

The default value is 1e-6.

重载 CVariationalGaussianLikelihood .

在文件 DualVariationalGaussianLikelihood.cpp72 行定义.

void set_strict_scale ( float64_t  strict_scale)
virtual

set the m_strict_scale

参数
strict_scalemust be between 0 and 1 exclusively

在文件 DualVariationalGaussianLikelihood.cpp103 行定义.

bool set_variational_distribution ( SGVector< float64_t mu,
SGVector< float64_t s2,
const CLabels lab 
)
virtual

set the variational distribution given data and parameters

参数
mumean of the variational distribution
s2variance of the variational distribution
lablabels/data used
返回
true if variational parameters are valid

Note that the variational distribution is Gaussian

重载 CVariationalGaussianLikelihood .

在文件 DualVariationalGaussianLikelihood.cpp96 行定义.

CSGObject * shallow_copy ( ) const
virtualinherited

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

CGaussianKernel 重载.

在文件 SGObject.cpp192 行定义.

bool supports_binary ( ) const
virtualinherited

return whether likelihood function supports binary classification

返回
boolean

重载 CLikelihoodModel .

在文件 VariationalLikelihood.cpp162 行定义.

bool supports_derivative_wrt_hyperparameter ( ) const
virtual

return whether likelihood function supports computing the derivative wrt hyperparameter Note that variational parameters are NOT considered as hyperparameters

返回
boolean

实现了 CVariationalLikelihood.

在文件 DualVariationalGaussianLikelihood.cpp84 行定义.

bool supports_multiclass ( ) const
virtualinherited

return whether likelihood function supports multiclass classification

返回
boolean

重载 CLikelihoodModel .

在文件 VariationalLikelihood.cpp168 行定义.

bool supports_regression ( ) const
virtualinherited

return whether likelihood function supports regression

返回
boolean

重载 CLikelihoodModel .

在文件 VariationalLikelihood.cpp156 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.cpp303 行定义.

void update_parameter_hash ( )
virtualinherited

Updates the hash of current parameter combination

在文件 SGObject.cpp248 行定义.

类成员变量说明

SGIO* io
inherited

io

在文件 SGObject.h369 行定义.

Parameter* m_gradient_parameters
inherited

parameters wrt which we can compute gradients

在文件 SGObject.h384 行定义.

uint32_t m_hash
inherited

Hash of parameter values

在文件 SGObject.h387 行定义.

bool m_is_valid
protected

whether m_lambda is satisfied lower bound and/or upper bound condition.

在文件 DualVariationalGaussianLikelihood.h238 行定义.

SGVector<float64_t> m_lab
protectedinherited

the label of data

在文件 VariationalLikelihood.h277 行定义.

SGVector<float64_t> m_lambda
protected

The dual variables (lambda) for the variational parameter s2.

Note that in variational Gaussian inference, there is a relationship between lambda and alpha, where alpha is the dual parameter for variational parameter mu

Therefore, the dual variables (alpha) for variational parameter mu is not explicitly saved.

在文件 DualVariationalGaussianLikelihood.h227 行定义.

CLikelihoodModel* m_likelihood
protectedinherited

the distribution used to model data

在文件 VariationalLikelihood.h280 行定义.

Parameter* m_model_selection_parameters
inherited

model selection parameters

在文件 SGObject.h381 行定义.

SGVector<float64_t> m_mu
protectedinherited

The mean of variational Gaussian distribution

在文件 VariationalGaussianLikelihood.h79 行定义.

Parameter* m_parameters
inherited

parameters

在文件 SGObject.h378 行定义.

SGVector<float64_t> m_s2
protectedinherited

The variance of variational Gaussian distribution

在文件 VariationalGaussianLikelihood.h82 行定义.

float64_t m_strict_scale
protected

The value used to ensure strict bound(s) for m_lambda in adjust_step_wrt_dual_parameter()

Note that the value should be between 0 and 1 exclusively.

The default value is 1e-5.

在文件 DualVariationalGaussianLikelihood.h235 行定义.

Parallel* parallel
inherited

parallel

在文件 SGObject.h372 行定义.

Version* version
inherited

version

在文件 SGObject.h375 行定义.


该类的文档由以下文件生成:

SHOGUN 机器学习工具包 - 项目文档