Covariance function for multi-output Gaussian Processes based on the linear model of coregionalization (LMC) More...

#include <LMC.h>

Inheritance diagram for LMC:

Public Types
typedef DataFileName	DataFileParameterType

Public Member Functions
	LMC (const InputParameters &parameters)

void	computeCovarianceMatrix (RealEigenMatrix &K, const RealEigenMatrix &x, const RealEigenMatrix &xp, const bool is_self_covariance) const override
	Generates the Covariance Matrix given two sets of points in the parameter space. More...

bool	computedKdhyper (RealEigenMatrix &dKdhp, const RealEigenMatrix &x, const std::string &hyper_param_name, unsigned int ind) const override
	Redirect dK/dhp for hyperparameter "hp". More...

void	loadHyperParamMap (const std::unordered_map< std::string, Real > &map, const std::unordered_map< std::string, std::vector< Real >> &vec_map)
	Load some hyperparameters into the local maps contained in this object. More...

void	buildHyperParamMap (std::unordered_map< std::string, Real > &map, std::unordered_map< std::string, std::vector< Real >> &vec_map) const
	Populates the input maps with the owned hyperparameters. More...

virtual bool	getTuningData (const std::string &name, unsigned int &size, Real &min, Real &max) const
	Get the default minimum and maximum and size of a hyperparameter. More...

void	dependentCovarianceTypes (std::map< UserObjectName, std::string > &name_type_map) const
	Populate a map with the names and types of the dependent covariance functions. More...

const std::vector< UserObjectName > &	dependentCovarianceNames () const
	Get the names of the dependent covariances. More...

virtual bool	isTunable (const std::string &name) const
	Check if a given parameter is tunable. More...

unsigned int	numOutputs () const
	Return the number of outputs assumed for this covariance function. More...

std::unordered_map< std::string, Real > &	hyperParamMapReal ()
	Get the map of scalar parameters. More...

std::unordered_map< std::string, std::vector< Real > > &	hyperParamMapVectorReal ()
	Get the map of vector parameters. More...

virtual bool	enabled () const

std::shared_ptr< MooseObject >	getSharedPtr ()

std::shared_ptr< const MooseObject >	getSharedPtr () const

MooseApp &	getMooseApp () const

const std::string &	type () const

virtual const std::string &	name () const

std::string	typeAndName () const

std::string	errorPrefix (const std::string &error_type) const

void	callMooseError (std::string msg, const bool with_prefix) const

MooseObjectParameterName	uniqueParameterName (const std::string &parameter_name) const

const InputParameters &	parameters () const

MooseObjectName	uniqueName () const

const T &	getParam (const std::string &name) const

std::vector< std::pair< T1, T2 > >	getParam (const std::string &param1, const std::string &param2) const

const T *	queryParam (const std::string &name) const

const T &	getRenamedParam (const std::string &old_name, const std::string &new_name) const

T	getCheckedPointerParam (const std::string &name, const std::string &error_string="") const

bool	isParamValid (const std::string &name) const

bool	isParamSetByUser (const std::string &nm) const

void	paramError (const std::string &param, Args... args) const

void	paramWarning (const std::string &param, Args... args) const

void	paramInfo (const std::string &param, Args... args) const

void	connectControllableParams (const std::string &parameter, const std::string &object_type, const std::string &object_name, const std::string &object_parameter) const

void	mooseError (Args &&... args) const

void	mooseErrorNonPrefixed (Args &&... args) const

void	mooseDocumentedError (const std::string &repo_name, const unsigned int issue_num, Args &&... args) const

void	mooseWarning (Args &&... args) const

void	mooseWarningNonPrefixed (Args &&... args) const

void	mooseDeprecated (Args &&... args) const

void	mooseInfo (Args &&... args) const

std::string	getDataFileName (const std::string &param) const

std::string	getDataFileNameByName (const std::string &relative_path) const

std::string	getDataFilePath (const std::string &relative_path) const

const Parallel::Communicator &	comm () const

processor_id_type	n_processors () const

processor_id_type	processor_id () const

Static Public Member Functions
static InputParameters	validParams ()

Public Attributes
const ConsoleStream	_console

Protected Member Functions
void	computeBMatrix (RealEigenMatrix &Bmat, const unsigned int exp_i) const
	Computes the covariance matrix for the outputs (using the latent coefficients) We use a $B = a_i a_i^T + diag(lambda_i)$ expansion here where $a_i$ and $lambda_i$ are vectors. More...

void	computeAGradient (RealEigenMatrix &grad, const unsigned int exp_i, const unsigned int index) const
	Computes the gradient of $B$ with respect to the entries in $a_i$ in the following expression: $B = a_i a_i^T + diag(lambda_i)$. More...

void	computeLambdaGradient (RealEigenMatrix &grad, const unsigned int exp_i, const unsigned int index) const
	Computes the gradient of $B$ with respect to the entries in $lambda_i$ in the following expression: $B = a_i a_i^T + diag(lambda_i)$. More...

const Real &	addRealHyperParameter (const std::string &name, const Real value, const bool is_tunable)
	Register a scalar hyperparameter to this covariance function. More...

const std::vector< Real > &	addVectorRealHyperParameter (const std::string &name, const std::vector< Real > value, const bool is_tunable)
	Register a vector hyperparameter to this covariance function. More...

CovarianceFunctionBase *	getCovarianceFunctionByName (const UserObjectName &name) const
	Lookup a CovarianceFunction object by name and return pointer. More...

Protected Attributes
const unsigned int	_num_expansion_terms
	The number of expansion terms in the output ovariance matrix. More...

std::unordered_map< std::string, Real >	_hp_map_real
	Map of real-valued hyperparameters. More...

std::unordered_map< std::string, std::vector< Real > >	_hp_map_vector_real
	Map of vector-valued hyperparameters. More...

std::unordered_set< std::string >	_tunable_hp
	list of tunable hyper-parameters More...

const unsigned int	_num_outputs
	The number of outputs this covariance function is used to describe. More...

const std::vector< UserObjectName >	_dependent_covariance_names
	The names of the dependent covariance functions. More...

std::vector< std::string >	_dependent_covariance_types
	The types of the dependent covariance functions. More...

std::vector< CovarianceFunctionBase * >	_covariance_functions
	Vector of pointers to the dependent covariance functions. More...

const bool &	_enabled

MooseApp &	_app

const std::string	_type

const std::string	_name

const InputParameters &	_pars

Factory &	_factory

ActionFactory &	_action_factory

const Parallel::Communicator &	_communicator

Private Attributes
std::vector< const std::vector< Real > * >	_a_coeffs
	The vectors in the $B = a_i a_i^T + diag(lambda_i)$ expansion. More...

std::vector< const std::vector< Real > * >	_lambdas

Detailed Description

Covariance function for multi-output Gaussian Processes based on the linear model of coregionalization (LMC)

Definition at line 18 of file LMC.h.

Constructor & Destructor Documentation

◆ LMC()

LMC::LMC ( const InputParameters & parameters )

Definition at line 29 of file LMC.C.

   : CovarianceFunctionBase(parameters),
     _num_expansion_terms(getParam<unsigned int>("num_latent_funcs"))
 {
   // We use a random number generator to obtain the initial guess for the
   // hyperparams
   MooseRandom generator_latent;
   generator_latent.seed(0, 1980);
 
   // First add and initialize the a A coefficients in the (aa^T+lambda*I) matrix
   for (const auto exp_i : make_range(_num_expansion_terms))
   {
     const std::string a_coeff_name = "acoeff_" + std::to_string(exp_i);
     const std::string a_coeff_name_with_prefix = _name + ":" + a_coeff_name;
     _a_coeffs.push_back(
         &addVectorRealHyperParameter(a_coeff_name, std::vector(_num_outputs, 1.0), true));
 
     auto & acoeff_vector = _hp_map_vector_real[a_coeff_name_with_prefix];
     for (const auto out_i : make_range(_num_outputs))
       acoeff_vector[out_i] = 3.0 * generator_latent.rand(0) + 1.0;
   }
 
   // Then add and initialize the lambda coefficients in the (aa^T+lambda*I) matrix
   for (const auto exp_i : make_range(_num_expansion_terms))
   {
     const std::string lambda_name = "lambda_" + std::to_string(exp_i);
     const std::string lambda_name_with_prefix = _name + ":" + lambda_name;
     _lambdas.push_back(
         &addVectorRealHyperParameter(lambda_name, std::vector(_num_outputs, 1.0), true));
 
     auto & lambda_vector = _hp_map_vector_real[lambda_name_with_prefix];
     for (const auto out_i : make_range(_num_outputs))
       lambda_vector[out_i] = 3.0 * generator_latent.rand(0) + 1.0;
   }
 }

Member Function Documentation

◆ addRealHyperParameter()

const Real & CovarianceFunctionBase::addRealHyperParameter	(	const std::string &	name,
		const Real	value,
		const bool	is_tunable
	)

protectedinherited

Register a scalar hyperparameter to this covariance function.

Parameters

name	The name of the parameter
value	The initial value of the parameter
is_tunable	If the parameter is tunable during optimization

Definition at line 52 of file CovarianceFunctionBase.C.

 {
   const auto prefixed_name = _name + ":" + name;
   if (is_tunable)
     _tunable_hp.insert(prefixed_name);
   return _hp_map_real.emplace(prefixed_name, value).first->second;
 }

◆ addVectorRealHyperParameter()

const std::vector< Real > & CovarianceFunctionBase::addVectorRealHyperParameter	(	const std::string &	name,
		const std::vector< Real >	value,
		const bool	is_tunable
	)

protectedinherited

Register a vector hyperparameter to this covariance function.

Parameters

name	The name of the parameter
value	The initial value of the parameter
is_tunable	If the parameter is tunable during optimization

Definition at line 63 of file CovarianceFunctionBase.C.

Referenced by LMC().

 {
   const auto prefixed_name = _name + ":" + name;
   if (is_tunable)
     _tunable_hp.insert(prefixed_name);
   return _hp_map_vector_real.emplace(prefixed_name, value).first->second;
 }

◆ buildHyperParamMap()

void CovarianceFunctionBase::buildHyperParamMap	(	std::unordered_map< std::string, Real > &	map,
		std::unordered_map< std::string, std::vector< Real >> &	vec_map
	)		const

inherited

Populates the input maps with the owned hyperparameters.

Parameters

map	Map of scalar hyperparameters that should be populated
vec_map	Map of vector hyperparameters that should be populated

Definition at line 115 of file CovarianceFunctionBase.C.

Referenced by StochasticTools::GaussianProcess::setupCovarianceMatrix(), and StochasticTools::GaussianProcess::tuneHyperParamsAdam().

 {
   // First, add the hyperparameters of the dependent covariance functions
   for (const auto dependent_covar : _covariance_functions)
     dependent_covar->buildHyperParamMap(map, vec_map);
 
   // At the end we just append the hyperparameters this object owns
   for (const auto & iter : _hp_map_real)
     map[iter.first] = iter.second;
   for (const auto & iter : _hp_map_vector_real)
     vec_map[iter.first] = iter.second;
 }

◆ computeAGradient()

void LMC::computeAGradient	(	RealEigenMatrix &	grad,
		const unsigned int	exp_i,
		const unsigned int	index
	)		const

protected

Computes the gradient of $B$ with respect to the entries in $a_i$ in the following expression: $B = a_i a_i^T + diag(lambda_i)$.

Parameters

grad	The gradient matrix that should be populated
exp_i	The index of the expansion of B
index	The index within the vector $a_i$

Definition at line 176 of file LMC.C.

Referenced by computedKdhyper().

 {
   const auto & a_coeffs = *_a_coeffs[exp_i];
   // Add asserts here
   grad.setZero();
   for (const auto col_i : make_range(_num_outputs))
     grad(index, col_i) = a_coeffs[col_i];
   const RealEigenMatrix transpose = grad.transpose();
   grad = grad + transpose;
 }

◆ computeBMatrix()

void LMC::computeBMatrix	(	RealEigenMatrix &	Bmat,
		const unsigned int	exp_i
	)		const

protected

Computes the covariance matrix for the outputs (using the latent coefficients) We use a $B = a_i a_i^T + diag(lambda_i)$ expansion here where $a_i$ and $lambda_i$ are vectors.

Parameters

Bmat	The matrix which should be populated by the covariance values
exp_i	The expansion index in the latent space

Definition at line 161 of file LMC.C.

Referenced by computeCovarianceMatrix(), and computedKdhyper().

 {
   const auto & a_coeffs = *_a_coeffs[exp_i];
   const auto & lambda_coeffs = *_lambdas[exp_i];
 
   for (const auto row_i : make_range(_num_outputs))
     for (const auto col_i : make_range(_num_outputs))
     {
       Bmat(row_i, col_i) = a_coeffs[row_i] * a_coeffs[col_i];
       if (row_i == col_i)
         Bmat(row_i, col_i) += lambda_coeffs[col_i];
     }
 }

◆ computeCovarianceMatrix()

void LMC::computeCovarianceMatrix	(	RealEigenMatrix &	K,
		const RealEigenMatrix &	x,
		const RealEigenMatrix &	xp,
		const bool	is_self_covariance
	)		const

overridevirtual

Generates the Covariance Matrix given two sets of points in the parameter space.

Parameters

K	Reference to a matrix which should be populated by the covariance entries
x	Reference to the first set of points
xp	Reference to the second set of points
is_self_covariance	Switch to enable adding the noise variance to the diagonal of the covariance matrix

Implements CovarianceFunctionBase.

Definition at line 66 of file LMC.C.

 {
   // Create temporary vectors for constructing the covariance matrix
   RealEigenMatrix K_params = RealEigenMatrix::Zero(x.rows(), xp.rows());
   RealEigenMatrix B = RealEigenMatrix::Zero(_num_outputs, _num_outputs);
   K = RealEigenMatrix::Zero(x.rows() * _num_outputs, xp.rows() * _num_outputs);
   RealEigenMatrix K_working =
       RealEigenMatrix::Zero(x.rows() * _num_outputs, xp.rows() * _num_outputs);
 
   // For every expansion term we add the contribution to the covariance matrix
   for (const auto exp_i : make_range(_num_expansion_terms))
   {
     _covariance_functions[exp_i]->computeCovarianceMatrix(K_params, x, xp, is_self_covariance);
     computeBMatrix(B, exp_i);
     MathUtils::kron(K_working, B, K_params);
     K += K_working;
   }
 }

◆ computedKdhyper()

bool LMC::computedKdhyper	(	RealEigenMatrix &	dKdhp,
		const RealEigenMatrix &	x,
		const std::string &	hyper_param_name,
		unsigned int	ind
	)		const

overridevirtual

Redirect dK/dhp for hyperparameter "hp".

Returns false is the parameter has not been found in this covariance object.

Parameters

dKdhp	The matrix which should be populated with the derivatives
x	The input vector for which the derivatives of the covariance matrix is computed
hyper_param_name	The name of the hyperparameter
ind	The index within the hyperparameter. 0 if it is a scalar parameter. If it is a vector parameter, it should be the index within the vector.

Reimplemented from CovarianceFunctionBase.

Definition at line 89 of file LMC.C.

 {
   // Early return in the paramter name is longer than the expected [name] prefix.
   // We prefix the parameter names with the name of the covariance function.
   if (name().length() + 1 > hyper_param_name.length())
     return false;
 
   // Strip the prefix from the given parameter name
   const std::string name_without_prefix = hyper_param_name.substr(name().length() + 1);
 
   // Check if the parameter is tunable
   if (_tunable_hp.find(hyper_param_name) != _tunable_hp.end())
   {
     const std::string acoeff_prefix = "acoeff_";
     const std::string lambda_prefix = "lambda_";
 
     // Allocate storage for the factors of the total gradient matrix
     RealEigenMatrix dBdhp = RealEigenMatrix::Zero(_num_outputs, _num_outputs);
     RealEigenMatrix K_params = RealEigenMatrix::Zero(x.rows(), x.rows());
 
     if (name_without_prefix.find(acoeff_prefix) != std::string::npos)
     {
       // Automatically grab the expansion index
       const int number = std::stoi(name_without_prefix.substr(acoeff_prefix.length()));
       computeAGradient(dBdhp, number, ind);
       _covariance_functions[number]->computeCovarianceMatrix(K_params, x, x, true);
     }
     else if (name_without_prefix.find(lambda_prefix) != std::string::npos)
     {
       // Automatically grab the expansion index
       const int number = std::stoi(name_without_prefix.substr(lambda_prefix.length()));
       computeLambdaGradient(dBdhp, number, ind);
       _covariance_functions[number]->computeCovarianceMatrix(K_params, x, x, true);
     }
     MathUtils::kron(dKdhp, dBdhp, K_params);
     return true;
   }
   else
   {
     // Allocate storage for the matrix factors
     RealEigenMatrix B_tmp = RealEigenMatrix::Zero(_num_outputs, _num_outputs);
     RealEigenMatrix B = RealEigenMatrix::Zero(_num_outputs, _num_outputs);
     RealEigenMatrix dKdhp_sub = RealEigenMatrix::Zero(x.rows(), x.rows());
 
     // First, check the dependent covariances
     bool found = false;
     for (const auto dependent_covar : _covariance_functions)
       if (!found)
         found = dependent_covar->computedKdhyper(dKdhp_sub, x, hyper_param_name, ind);
 
     if (!found)
       mooseError("Hyperparameter ", hyper_param_name, "not found!");
 
     // Then we compute the output covariance
     for (const auto exp_i : make_range(_num_expansion_terms))
     {
       computeBMatrix(B_tmp, exp_i);
       B += B_tmp;
     }
 
     MathUtils::kron(dKdhp, B, dKdhp_sub);
 
     return true;
   }
 
   return false;
 }

◆ computeLambdaGradient()

void LMC::computeLambdaGradient	(	RealEigenMatrix &	grad,
		const unsigned int	exp_i,
		const unsigned int	index
	)		const

protected

Computes the gradient of $B$ with respect to the entries in $lambda_i$ in the following expression: $B = a_i a_i^T + diag(lambda_i)$.

Parameters

grad	The gradient matrix that should be populated
exp_i	The index of the expansion of B
index	The index within the vector $lambda_i$

Definition at line 190 of file LMC.C.

Referenced by computedKdhyper().

 {
   grad.setZero();
   grad(index, index) = 1.0;
 }

◆ dependentCovarianceNames()

const std::vector<UserObjectName>& CovarianceFunctionBase::dependentCovarianceNames ( ) const

inlineinherited

Get the names of the dependent covariances.

Definition at line 62 of file CovarianceFunctionBase.h.

Referenced by StochasticTools::GaussianProcess::linkCovarianceFunction().

   {
     return _dependent_covariance_names;
   }

◆ dependentCovarianceTypes()

void CovarianceFunctionBase::dependentCovarianceTypes ( std::map< UserObjectName, std::string > & name_type_map ) const

inherited

Populate a map with the names and types of the dependent covariance functions.

Parameters

name_type_map Reference to the map which should be populated

Definition at line 163 of file CovarianceFunctionBase.C.

Referenced by StochasticTools::GaussianProcess::linkCovarianceFunction().

 {
   for (const auto dependent_covar : _covariance_functions)
   {
     dependent_covar->dependentCovarianceTypes(name_type_map);
     name_type_map.insert(std::make_pair(dependent_covar->name(), dependent_covar->type()));
   }
 }

◆ getCovarianceFunctionByName()

CovarianceFunctionBase * CovarianceInterface::getCovarianceFunctionByName ( const UserObjectName & name ) const

protectedinherited

Lookup a CovarianceFunction object by name and return pointer.

Definition at line 25 of file CovarianceInterface.C.

Referenced by ActiveLearningGaussianProcess::ActiveLearningGaussianProcess(), CovarianceFunctionBase::CovarianceFunctionBase(), GaussianProcessTrainer::GaussianProcessTrainer(), and GaussianProcessSurrogate::setupCovariance().

 {
   std::vector<CovarianceFunctionBase *> models;
   _covar_feproblem.theWarehouse()
       .query()
       .condition<AttribName>(name)
       .condition<AttribSystem>("CovarianceFunction")
       .queryInto(models);
   if (models.empty())
     mooseError("Unable to find a CovarianceFunction object with the name '" + name + "'");
   return models[0];
 }

◆ getTuningData()

bool CovarianceFunctionBase::getTuningData	(	const std::string &	name,
		unsigned int &	size,
		Real &	min,
		Real &	max
	)		const

virtualinherited

Get the default minimum and maximum and size of a hyperparameter.

Returns false is the parameter has not been found in this covariance object.

Parameters

name	The name of the hyperparameter
size	Reference to an unsigned int that will contain the size of the hyperparameter (will be populated with 1 if it is scalar)
min	Reference to a number which will be populated by the maximum allowed value of the hyperparameter
max	Reference to a number which will be populated by the minimum allowed value of the hyperparameter

Definition at line 131 of file CovarianceFunctionBase.C.

Referenced by StochasticTools::GaussianProcess::generateTuningMap().

 {
   // First, check the dependent covariances
   for (const auto dependent_covar : _covariance_functions)
     if (dependent_covar->getTuningData(name, size, min, max))
       return true;
 
   min = 1e-9;
   max = 1e9;
 
   if (_hp_map_real.find(name) != _hp_map_real.end())
   {
     size = 1;
     return true;
   }
   else if (_hp_map_vector_real.find(name) != _hp_map_vector_real.end())
   {
     const auto & vector_value = _hp_map_vector_real.find(name);
     size = vector_value->second.size();
     return true;
   }
   else
   {
     size = 0;
     return false;
   }
 }

◆ hyperParamMapReal()

std::unordered_map<std::string, Real>& CovarianceFunctionBase::hyperParamMapReal ( )

inlineinherited

Get the map of scalar parameters.

Definition at line 88 of file CovarianceFunctionBase.h.

88 { return _hp_map_real; }

CovarianceFunctionBase::_hp_map_real

std::unordered_map< std::string, Real > _hp_map_real

Map of real-valued hyperparameters.

Definition: CovarianceFunctionBase.h:113

◆ hyperParamMapVectorReal()

std::unordered_map<std::string, std::vector<Real> >& CovarianceFunctionBase::hyperParamMapVectorReal ( )

inlineinherited

Get the map of vector parameters.

Definition at line 91 of file CovarianceFunctionBase.h.

   {
     return _hp_map_vector_real;
   }

◆ isTunable()

bool CovarianceFunctionBase::isTunable ( const std::string & name ) const

virtualinherited

Check if a given parameter is tunable.

Parameters

The	name of the hyperparameter

Definition at line 74 of file CovarianceFunctionBase.C.

Referenced by StochasticTools::GaussianProcess::generateTuningMap().

 {
   // First, we check if the dependent covariances have the parameter
   for (const auto dependent_covar : _covariance_functions)
     if (dependent_covar->isTunable(name))
       return true;
 
   if (_tunable_hp.find(name) != _tunable_hp.end())
     return true;
   else if (_hp_map_real.find(name) != _hp_map_real.end() ||
            _hp_map_vector_real.find(name) != _hp_map_vector_real.end())
     mooseError("We found hyperparameter ", name, " but it was not declared tunable!");
 
   return false;
 }

◆ loadHyperParamMap()

void CovarianceFunctionBase::loadHyperParamMap	(	const std::unordered_map< std::string, Real > &	map,
		const std::unordered_map< std::string, std::vector< Real >> &	vec_map
	)

inherited

Load some hyperparameters into the local maps contained in this object.

Parameters

map	Input map of scalar hyperparameters
vec_map	Input map of vector hyperparameters

Definition at line 91 of file CovarianceFunctionBase.C.

Referenced by LoadCovarianceDataAction::load(), and StochasticTools::GaussianProcess::tuneHyperParamsAdam().

 {
   // First, load the hyperparameters of the dependent covariance functions
   for (const auto dependent_covar : _covariance_functions)
     dependent_covar->loadHyperParamMap(map, vec_map);
 
   // Then we load the hyperparameters of this object
   for (auto & iter : _hp_map_real)
   {
     const auto & map_iter = map.find(iter.first);
     if (map_iter != map.end())
       iter.second = map_iter->second;
   }
   for (auto & iter : _hp_map_vector_real)
   {
     const auto & map_iter = vec_map.find(iter.first);
     if (map_iter != vec_map.end())
       iter.second = map_iter->second;
   }
 }

◆ numOutputs()

unsigned int CovarianceFunctionBase::numOutputs ( ) const

inlineinherited

Return the number of outputs assumed for this covariance function.

Definition at line 85 of file CovarianceFunctionBase.h.

Referenced by GaussianProcessSurrogate::evaluate(), GaussianProcessTrainer::GaussianProcessTrainer(), and StochasticTools::GaussianProcess::linkCovarianceFunction().

85 { return _num_outputs; }

CovarianceFunctionBase::_num_outputs

const unsigned int _num_outputs

The number of outputs this covariance function is used to describe.

Definition: CovarianceFunctionBase.h:122

◆ validParams()

InputParameters LMC::validParams ( )

static

Definition at line 17 of file LMC.C.

 {
   InputParameters params = CovarianceFunctionBase::validParams();
   params.addClassDescription("Covariance function for multioutput Gaussian Processes based on the "
                              "Linear Model of Coregionalization (LMC).");
   params.addParam<unsigned int>(
       "num_latent_funcs", 1., "The number of latent functions for the expansion of the outputs.");
   params.makeParamRequired<unsigned int>("num_outputs");
   params.makeParamRequired<std::vector<UserObjectName>>("covariance_functions");
   return params;
 }

Member Data Documentation

◆ _a_coeffs

std::vector<const std::vector<Real> *> LMC::_a_coeffs

private

The vectors in the $B = a_i a_i^T + diag(lambda_i)$ expansion.

Definition at line 72 of file LMC.h.

Referenced by computeAGradient(), computeBMatrix(), and LMC().

◆ _covariance_functions

std::vector<CovarianceFunctionBase *> CovarianceFunctionBase::_covariance_functions

protectedinherited

Vector of pointers to the dependent covariance functions.

Definition at line 131 of file CovarianceFunctionBase.h.

Referenced by CovarianceFunctionBase::buildHyperParamMap(), computeCovarianceMatrix(), computedKdhyper(), CovarianceFunctionBase::CovarianceFunctionBase(), CovarianceFunctionBase::dependentCovarianceTypes(), CovarianceFunctionBase::getTuningData(), CovarianceFunctionBase::isTunable(), and CovarianceFunctionBase::loadHyperParamMap().

◆ _dependent_covariance_names

const std::vector<UserObjectName> CovarianceFunctionBase::_dependent_covariance_names

protectedinherited

The names of the dependent covariance functions.

Definition at line 125 of file CovarianceFunctionBase.h.

Referenced by CovarianceFunctionBase::CovarianceFunctionBase(), and CovarianceFunctionBase::dependentCovarianceNames().

◆ _dependent_covariance_types

std::vector<std::string> CovarianceFunctionBase::_dependent_covariance_types

protectedinherited

The types of the dependent covariance functions.

Definition at line 128 of file CovarianceFunctionBase.h.

Referenced by CovarianceFunctionBase::CovarianceFunctionBase().

◆ _hp_map_real

std::unordered_map<std::string, Real> CovarianceFunctionBase::_hp_map_real

protectedinherited

Map of real-valued hyperparameters.

Definition at line 113 of file CovarianceFunctionBase.h.

Referenced by CovarianceFunctionBase::addRealHyperParameter(), CovarianceFunctionBase::buildHyperParamMap(), CovarianceFunctionBase::getTuningData(), CovarianceFunctionBase::hyperParamMapReal(), CovarianceFunctionBase::isTunable(), and CovarianceFunctionBase::loadHyperParamMap().

◆ _hp_map_vector_real

std::unordered_map<std::string, std::vector<Real> > CovarianceFunctionBase::_hp_map_vector_real

protectedinherited

Map of vector-valued hyperparameters.

Definition at line 116 of file CovarianceFunctionBase.h.

Referenced by CovarianceFunctionBase::addVectorRealHyperParameter(), CovarianceFunctionBase::buildHyperParamMap(), CovarianceFunctionBase::getTuningData(), CovarianceFunctionBase::hyperParamMapVectorReal(), CovarianceFunctionBase::isTunable(), LMC(), and CovarianceFunctionBase::loadHyperParamMap().

◆ _lambdas

std::vector<const std::vector<Real> *> LMC::_lambdas

private

Definition at line 73 of file LMC.h.

Referenced by computeBMatrix(), and LMC().

◆ _num_expansion_terms

const unsigned int LMC::_num_expansion_terms

protected

The number of expansion terms in the output ovariance matrix.

Definition at line 67 of file LMC.h.

Referenced by computeCovarianceMatrix(), computedKdhyper(), and LMC().

◆ _num_outputs

const unsigned int CovarianceFunctionBase::_num_outputs

protectedinherited

The number of outputs this covariance function is used to describe.

Definition at line 122 of file CovarianceFunctionBase.h.

Referenced by computeAGradient(), computeBMatrix(), computeCovarianceMatrix(), computedKdhyper(), LMC(), and CovarianceFunctionBase::numOutputs().

◆ _tunable_hp

std::unordered_set<std::string> CovarianceFunctionBase::_tunable_hp

protectedinherited

list of tunable hyper-parameters

Definition at line 119 of file CovarianceFunctionBase.h.

Referenced by CovarianceFunctionBase::addRealHyperParameter(), CovarianceFunctionBase::addVectorRealHyperParameter(), computedKdhyper(), and CovarianceFunctionBase::isTunable().

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

stochastic_tools/include/covariances/LMC.h
stochastic_tools/src/covariances/LMC.C

Public Types

Public Member Functions

Static Public Member Functions

Public Attributes

Protected Member Functions

Protected Attributes

Private Attributes

Detailed Description

Constructor & Destructor Documentation

◆ LMC()

Member Function Documentation

◆ addRealHyperParameter()

◆ addVectorRealHyperParameter()

◆ buildHyperParamMap()

◆ computeAGradient()

◆ computeBMatrix()

◆ computeCovarianceMatrix()

◆ computedKdhyper()

◆ computeLambdaGradient()

◆ dependentCovarianceNames()

◆ dependentCovarianceTypes()

◆ getCovarianceFunctionByName()

◆ getTuningData()

◆ hyperParamMapReal()

◆ hyperParamMapVectorReal()

◆ isTunable()

◆ loadHyperParamMap()

◆ numOutputs()

◆ validParams()

Member Data Documentation

◆ _a_coeffs

◆ _covariance_functions

◆ _dependent_covariance_names

◆ _dependent_covariance_types

◆ _hp_map_real

◆ _hp_map_vector_real

◆ _lambdas

◆ _num_expansion_terms

◆ _num_outputs

◆ _tunable_hp