muq::SamplingAlgorithms::ImportanceSampling Class Reference

Defines an imporance sampline sampler. More...

#include <ImportanceSampling.h>

Inheritance diagram for muq::SamplingAlgorithms::ImportanceSampling:

Detailed Description

Defines an imporance sampline sampler.

Configuration Parameters:

Parameter Key	Type	Default Value	Description
"NumSamples"	Int	-	The total number of steps (including burnin) to take, i.e., the length of the Markov chain.

Definition at line 22 of file ImportanceSampling.h.

Public Member Functions
	ImportanceSampling (std::shared_ptr< muq::Modeling::Distribution > const &target, boost::property_tree::ptree const &pt)
	ImportanceSampling (std::shared_ptr< muq::Modeling::ModPiece > const &target, std::shared_ptr< muq::Modeling::Distribution > const &bias, boost::property_tree::ptree const &pt)
	ImportanceSampling (std::shared_ptr< muq::Modeling::ModPiece > const &target, std::shared_ptr< muq::Modeling::Distribution > const &bias, std::vector< Eigen::VectorXd > hyperparameters, boost::property_tree::ptree const &pt)
	ImportanceSampling (std::shared_ptr< muq::Modeling::Distribution > const &target, std::vector< Eigen::VectorXd > hyperparameters, boost::property_tree::ptree const &pt)
virtual	~ImportanceSampling ()=default
Public Member Functions inherited from muq::SamplingAlgorithms::SamplingAlgorithm
	SamplingAlgorithm (std::shared_ptr< SampleCollection > const &samples)
	SamplingAlgorithm (std::shared_ptr< SampleCollection > const &samplesIn, std::shared_ptr< SampleCollection > const &QOIsIn)
	SamplingAlgorithm (std::shared_ptr< SampleCollection > const &samplesIn, std::shared_ptr< parcer::Communicator > const &comm)
virtual	~SamplingAlgorithm ()=default
virtual std::shared_ptr< SampleCollection >	GetSamples () const
virtual std::shared_ptr< SampleCollection >	GetQOIs () const
virtual void	SetState (std::vector< Eigen::VectorXd > const &x0)
virtual std::shared_ptr< SampleCollection >	Run (std::vector< Eigen::VectorXd > const &x0=std::vector< Eigen::VectorXd >())
template<typename... Args>
std::shared_ptr< SampleCollection >	Run (Args const &... args)
std::shared_ptr< parcer::Communicator >	GetCommunicator () const

Constructor & Destructor Documentation

ImportanceSampling() [1/4]

ImportanceSampling::ImportanceSampling	(	std::shared_ptr< muq::Modeling::Distribution > const &	target,
		boost::property_tree::ptree const &	pt
	)

Use the target distribution as the baising distribution. This is equivalent to Monte Carlo

Parameters

[in]	target	The target distribution
[in]	pt	Options for the importance sampler

Definition at line 11 of file ImportanceSampling.cpp.

ImportanceSampling() [2/4]

muq::SamplingAlgorithms::ImportanceSampling::ImportanceSampling	(	std::shared_ptr< muq::Modeling::ModPiece > const &	target,
		std::shared_ptr< muq::Modeling::Distribution > const &	bias,
		boost::property_tree::ptree const &	pt
	)

Parameters

[in]	target	The target distribution
[in]	bias	The biasing distribution
[in]	pt	Options for the importance sampler

ImportanceSampling() [3/4]

muq::SamplingAlgorithms::ImportanceSampling::ImportanceSampling	(	std::shared_ptr< muq::Modeling::ModPiece > const &	target,
		std::shared_ptr< muq::Modeling::Distribution > const &	bias,
		std::vector< Eigen::VectorXd >	hyperparameters,
		boost::property_tree::ptree const &	pt
	)

Parameters

[in]	target	The target distribution
[in]	bias	The biasing distribution
[in]	hyperparameters	Hyperparameters for the biasing distribution
[in]	pt	Options for the importance sampler

ImportanceSampling() [4/4]

muq::SamplingAlgorithms::ImportanceSampling::ImportanceSampling	(	std::shared_ptr< muq::Modeling::Distribution > const &	target,
		std::vector< Eigen::VectorXd >	hyperparameters,
		boost::property_tree::ptree const &	pt
	)

Parameters

[in]	target	The target distribution
[in]	hyperparameters	Hyperparameters for the biasing distribution
[in]	pt	Options for the importance sampler

~ImportanceSampling()

virtual muq::SamplingAlgorithms::ImportanceSampling::~ImportanceSampling ( )

virtualdefault

Member Function Documentation

RunImpl()

std::shared_ptr< SampleCollection > ImportanceSampling::RunImpl ( std::vector< Eigen::VectorXd > const &  x0 )

overrideprivatevirtual

Implements muq::SamplingAlgorithms::SamplingAlgorithm.

Definition at line 20 of file ImportanceSampling.cpp.

References bias, hyperparameters, numSamps, muq::SamplingAlgorithms::SamplingAlgorithm::samples, and target.

Member Data Documentation

bias

std::shared_ptr<muq::Modeling::Distribution> muq::SamplingAlgorithms::ImportanceSampling::bias

private

The biasing distribution.

Definition at line 67 of file ImportanceSampling.h.

Referenced by RunImpl().

hyperparameters

const std::vector<Eigen::VectorXd> muq::SamplingAlgorithms::ImportanceSampling::hyperparameters = std::vector<Eigen::VectorXd>()

private

Hyperparameters for the biasing distribution.

Definition at line 70 of file ImportanceSampling.h.

Referenced by RunImpl().

numSamps

const unsigned int muq::SamplingAlgorithms::ImportanceSampling::numSamps

private

The number of samples.

Definition at line 61 of file ImportanceSampling.h.

Referenced by RunImpl().

target

std::shared_ptr<muq::Modeling::ModPiece> muq::SamplingAlgorithms::ImportanceSampling::target

private

Definition at line 64 of file ImportanceSampling.h.

Referenced by RunImpl().

---

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

• doxygen_prep/MUQ/SamplingAlgorithms/ImportanceSampling.h
• doxygen_prep/modules/SamplingAlgorithms/src/ImportanceSampling.cpp