Detailed Description

Abstract base class for MCMC and Importance Sampling problems.

Assumes we are interested in sampling some probability density \(\pi(x_1, x_2, \ldots, x_N)\), where each input \(x_i\) is a vector valued block. For instance, \(x_1\) could be a Gaussian random variable and \(x_2\) could be a vector containing the mean and variance hyperparameters. The block structure is primarily used in Gibbs or Metropolis-in-Gibbs MCMC algorithms.

Both the number of blocks and the size of the blocks are stored. However, if one of the blocks is not a vector type, it is safe to set the block size to -1.

Definition at line 29 of file AbstractSamplingProblem.h.

Public Member Functions
	AbstractSamplingProblem (Eigen::VectorXi const &blockSizesIn, Eigen::VectorXi const &blockSizesQOIIn)

	AbstractSamplingProblem (Eigen::VectorXi const &blockSizesIn)

virtual	~AbstractSamplingProblem ()=default

virtual double	LogDensity (std::shared_ptr< SamplingState > const &state)=0

virtual std::shared_ptr< AbstractSamplingProblem >	Clone () const

virtual Eigen::VectorXd	GradLogDensity (std::shared_ptr< SamplingState > const &state, unsigned const blockWrt)

virtual std::shared_ptr< SamplingState >	QOI ()

virtual void	AddOptions (boost::property_tree::ptree &pt) const

Public Attributes
const int	numBlocks

const Eigen::VectorXi	blockSizes

const int	numBlocksQOI

const Eigen::VectorXi	blockSizesQOI

Constructor & Destructor Documentation

◆ AbstractSamplingProblem() [1/2]

AbstractSamplingProblem::AbstractSamplingProblem	(	Eigen::VectorXi const &	blockSizesIn,
		Eigen::VectorXi const &	blockSizesQOIIn
	)

Definition at line 8 of file AbstractSamplingProblem.cpp.

References blockSizes, blockSizesQOI, numBlocks, and numBlocksQOI.

◆ AbstractSamplingProblem() [2/2]

AbstractSamplingProblem::AbstractSamplingProblem ( Eigen::VectorXi const & blockSizesIn )

Definition at line 19 of file AbstractSamplingProblem.cpp.

◆ ~AbstractSamplingProblem()

virtual muq::SamplingAlgorithms::AbstractSamplingProblem::~AbstractSamplingProblem ( )

virtualdefault

Member Function Documentation

◆ AddOptions()

virtual void muq::SamplingAlgorithms::AbstractSamplingProblem::AddOptions ( boost::property_tree::ptree & pt ) const

inlinevirtual

Sometimes, there will be problem-specific options that need to be passed to the SamplingAlgorithm. This function adds any of those options to the given property_tree.

Reimplemented in muq::SamplingAlgorithms::ExpensiveSamplingProblem.

Definition at line 56 of file AbstractSamplingProblem.h.