#include <ConcatenateKernel.h>

Inheritance diagram for muq::Approximation::ConcatenateKernel:

Detailed Description

   @class ConcatenateKernel
   @ingroup CovarianceKernels
   @brief Concatenates two kernels together.
   @details Let \f$k_1(x,x^\prime)\f$ and \f$k_2(x,x^\prime)\f$ be two different covariance kernels with the same inputs.  This class describes a concatenated kernel of the form

\[ k(x,x^\prime) = \left[\begin{array}{cc}k_1(x,x^\prime) & 0\\ 0 & k_2(x,x^\prime)\end{array}\right]. \]

Definition at line 21 of file ConcatenateKernel.h.

Public Member Functions
	ConcatenateKernel (std::shared_ptr< KernelBase > const &kernel1In, std::shared_ptr< KernelBase > const &kernel2In)

	ConcatenateKernel (std::vector< std::shared_ptr< KernelBase >> const &kernelsIn)

virtual	~ConcatenateKernel ()=default

virtual std::shared_ptr< KernelBase >	Clone () const override

virtual void	FillBlock (Eigen::Ref< const Eigen::VectorXd > const &x1, Eigen::Ref< const Eigen::VectorXd > const &x2, Eigen::Ref< const Eigen::VectorXd > const &params, Eigen::Ref< Eigen::MatrixXd > block) const override

virtual void	FillPosDerivBlock (Eigen::Ref< const Eigen::VectorXd > const &x1, Eigen::Ref< const Eigen::VectorXd > const &x2, Eigen::Ref< const Eigen::VectorXd > const &params, std::vector< int > const &wrts, Eigen::Ref< Eigen::MatrixXd > block) const override

virtual std::tuple< std::shared_ptr< muq::Modeling::LinearSDE >, std::shared_ptr< muq::Modeling::LinearOperator >, Eigen::MatrixXd >	GetStateSpace (boost::property_tree::ptree sdeOptions=boost::property_tree::ptree()) const override
	Returns a state space representation of the covariance kernel. More...

Public Member Functions inherited from muq::Approximation::KernelBase
	KernelBase (unsigned int inputDimIn, unsigned int coDimIn, unsigned int numParamsIn)

	KernelBase (unsigned int inputDimIn, std::vector< unsigned int > dimIndsIn, unsigned int coDimIn, unsigned int numParamsIn)

virtual	~KernelBase ()

virtual std::vector< std::shared_ptr< KernelBase > >	GetSeperableComponents ()
	Overridden by ProductKernel. More...

virtual Eigen::MatrixXd	Evaluate (Eigen::VectorXd const &x1, Eigen::VectorXd const &x2) const

virtual Eigen::MatrixXd	BuildCovariance (Eigen::MatrixXd const &x) const

virtual Eigen::MatrixXd	BuildCovariance (Eigen::MatrixXd const &x1, Eigen::MatrixXd const &x2) const

virtual void	FillCovariance (Eigen::MatrixXd const &xs, Eigen::MatrixXd const &ys, Eigen::Ref< Eigen::MatrixXd > cov) const

virtual void	FillCovariance (Eigen::MatrixXd const &xs, Eigen::Ref< Eigen::MatrixXd > cov) const

virtual void	FillDerivCovariance (Eigen::MatrixXd const &xs, Eigen::MatrixXd const &ys, std::vector< int > const &wrts, Eigen::Ref< Eigen::MatrixXd > cov) const

virtual Eigen::MatrixXd	GetPosDerivative (Eigen::VectorXd const &x1, Eigen::VectorXd const &x2, std::vector< int > const &wrts) const
	Returns derivatives of the kernel with respect to the first input, x1. More...

virtual Eigen::MatrixXd	GetParamBounds () const

virtual Eigen::VectorXd	GetParams () const

virtual void	SetParams (Eigen::VectorXd const &params)

Additional Inherited Members
Public Attributes inherited from muq::Approximation::KernelBase
const std::vector< unsigned int >	dimInds

const unsigned int	inputDim

const unsigned int	coDim

const unsigned int	numParams

Constructor & Destructor Documentation

◆ ConcatenateKernel() [1/2]

muq::Approximation::ConcatenateKernel::ConcatenateKernel	(	std::shared_ptr< KernelBase > const &	kernel1In,
		std::shared_ptr< KernelBase > const &	kernel2In
	)

inline

Definition at line 26 of file ConcatenateKernel.h.

◆ ConcatenateKernel() [2/2]

ConcatenateKernel::ConcatenateKernel ( std::vector< std::shared_ptr< KernelBase >> const & kernelsIn )

Definition at line 9 of file ConcatenateKernel.cpp.

References muq::Approximation::KernelBase::cachedParams, kernels, and muq::Approximation::KernelBase::numParams.

◆ ~ConcatenateKernel()

virtual muq::Approximation::ConcatenateKernel::~ConcatenateKernel ( )

virtualdefault

Member Function Documentation

◆ Clone()

virtual std::shared_ptr<KernelBase> muq::Approximation::ConcatenateKernel::Clone ( ) const

inlineoverridevirtual

Implements muq::Approximation::KernelBase.

Definition at line 33 of file ConcatenateKernel.h.

References kernels.

◆ CountCoDims()

unsigned int ConcatenateKernel::CountCoDims ( std::vector< std::shared_ptr< KernelBase >> kernels )

staticprivate

Definition at line 72 of file ConcatenateKernel.cpp.

◆ CountParams()

unsigned int ConcatenateKernel::CountParams ( std::vector< std::shared_ptr< KernelBase >> kernels )

staticprivate

Definition at line 79 of file ConcatenateKernel.cpp.

◆ FillBlock()

void ConcatenateKernel::FillBlock	(	Eigen::Ref< const Eigen::VectorXd > const &	x1,
		Eigen::Ref< const Eigen::VectorXd > const &	x2,
		Eigen::Ref< const Eigen::VectorXd > const &	params,
		Eigen::Ref< Eigen::MatrixXd >	block
	)		const

overridevirtual

For particular points and parameters, this function fills in one block of the covariance matrix.

Implements muq::Approximation::KernelBase.

Definition at line 28 of file ConcatenateKernel.cpp.

References muq::Approximation::KernelBase::coDim, and kernels.

◆ FillPosDerivBlock()

void ConcatenateKernel::FillPosDerivBlock	(	Eigen::Ref< const Eigen::VectorXd > const &	x1,
		Eigen::Ref< const Eigen::VectorXd > const &	x2,
		Eigen::Ref< const Eigen::VectorXd > const &	params,
		std::vector< int > const &	wrts,
		Eigen::Ref< Eigen::MatrixXd >	block
	)		const

overridevirtual

Evaluates a first or higher order derivative of the covariance kernel with respect to one of the position variables.

Implements muq::Approximation::KernelBase.

Definition at line 49 of file ConcatenateKernel.cpp.

References muq::Approximation::KernelBase::coDim, and kernels.

◆ GetStateSpace()

std::tuple< std::shared_ptr< muq::Modeling::LinearSDE >, std::shared_ptr< muq::Modeling::LinearOperator >, Eigen::MatrixXd > ConcatenateKernel::GetStateSpace ( boost::property_tree::ptree sdeOptions = boost::property_tree::ptree() ) const

overridevirtual

Returns a state space representation of the covariance kernel.

If this is a one dimensional kernel (i.e., inputDim=1 and coDim=1), this function returns a state space representation of the covariance kernel. In particular, it returns a linear time invariant stochastic differential equation, whose solution, when started with the returned stationary covariance, provides the same information as this Gaussian process. The first component of the vector-valued stochastic differential equation is related to the Gaussian process. See "Kalman filtering and smoothing solutions to temporal Gaussian process regression models," by Jouni Hartikainen and Simo Sarkka, for more information.

Reimplemented from muq::Approximation::KernelBase.

Definition at line 88 of file ConcatenateKernel.cpp.

References kernels.

Member Data Documentation

◆ kernels

std::vector<std::shared_ptr<KernelBase> > muq::Approximation::ConcatenateKernel::kernels

private

Definition at line 53 of file ConcatenateKernel.h.

Referenced by Clone(), ConcatenateKernel(), FillBlock(), FillPosDerivBlock(), and GetStateSpace().

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

doxygen_prep/MUQ/Approximation/GaussianProcesses/ConcatenateKernel.h
doxygen_prep/modules/Approximation/src/GaussianProcesses/ConcatenateKernel.cpp

Detailed Description

Public Member Functions

Additional Inherited Members

Constructor & Destructor Documentation

◆ ConcatenateKernel() [1/2]

◆ ConcatenateKernel() [2/2]

◆ ~ConcatenateKernel()

Member Function Documentation

◆ Clone()

◆ CountCoDims()

◆ CountParams()

◆ FillBlock()

◆ FillPosDerivBlock()

◆ GetStateSpace()

Member Data Documentation

◆ kernels