A class used to perform Adaptive Importance Sampling using a Markov Chain Monte Carlo algorithm. More...

#include <AdaptiveImportanceSampler.h>

Inheritance diagram for AdaptiveImportanceSampler:

Public Types
enum	SampleMode { SampleMode::GLOBAL, SampleMode::LOCAL }

typedef DataFileName	DataFileParameterType

Public Member Functions
	AdaptiveImportanceSampler (const InputParameters &parameters)

const std::vector< Real > &	getInitialValues () const

const int &	getNumSamplesTrain () const

const bool &	getUseAbsoluteValue () const

const Real &	getOutputLimit () const

const std::vector< Real > &	getImportanceVectorMean () const

const std::vector< Real > &	getImportanceVectorStd () const

const std::vector< const Distribution * > &	getDistributionNames () const

const Real &	getStdFactor () const

virtual bool	isAdaptiveSamplingCompleted () const override
	Returns true if the adaptive sampling is completed. More...

std::vector< Real >	getNextLocalRow ()

dof_id_type	getNumberOfRows () const

dof_id_type	getNumberOfCols () const

dof_id_type	getNumberOfLocalRows () const

const LocalRankConfig &	getRankConfig (bool batch_mode) const

libMesh::Parallel::Communicator &	getLocalComm ()

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

virtual void	initialSetup ()

virtual void	timestepSetup ()

virtual void	jacobianSetup ()

virtual void	residualSetup ()

virtual void	subdomainSetup ()

virtual void	customSetup (const ExecFlagType &)

const ExecFlagEnum &	getExecuteOnEnum () const

PerfGraph &	perfGraph ()

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

Sampler &	getSampler (const std::string &name)

T &	getSamplerByName (const SamplerName &name)

Sampler &	getSamplerByName (const SamplerName &name)

const VectorPostprocessorValue &	getVectorPostprocessorValue (const std::string &param_name, const std::string &vector_name) const

const VectorPostprocessorValue &	getVectorPostprocessorValue (const std::string &param_name, const std::string &vector_name, bool needs_broadcast) const

const VectorPostprocessorValue &	getVectorPostprocessorValueByName (const VectorPostprocessorName &name, const std::string &vector_name) const

const VectorPostprocessorValue &	getVectorPostprocessorValueByName (const VectorPostprocessorName &name, const std::string &vector_name, bool needs_broadcast) const

const VectorPostprocessorValue &	getVectorPostprocessorValueOld (const std::string &param_name, const std::string &vector_name) const

const VectorPostprocessorValue &	getVectorPostprocessorValueOld (const std::string &param_name, const std::string &vector_name, bool needs_broadcast) const

const VectorPostprocessorValue &	getVectorPostprocessorValueOldByName (const VectorPostprocessorName &name, const std::string &vector_name) const

const VectorPostprocessorValue &	getVectorPostprocessorValueOldByName (const VectorPostprocessorName &name, const std::string &vector_name, bool needs_broadcast) const

const ScatterVectorPostprocessorValue &	getScatterVectorPostprocessorValue (const std::string &param_name, const std::string &vector_name) const

const ScatterVectorPostprocessorValue &	getScatterVectorPostprocessorValueByName (const VectorPostprocessorName &name, const std::string &vector_name) const

const ScatterVectorPostprocessorValue &	getScatterVectorPostprocessorValueOld (const std::string &param_name, const std::string &vector_name) const

const ScatterVectorPostprocessorValue &	getScatterVectorPostprocessorValueOldByName (const VectorPostprocessorName &name, const std::string &vector_name) const

bool	hasVectorPostprocessor (const std::string &param_name, const std::string &vector_name) const

bool	hasVectorPostprocessor (const std::string &param_name) const

bool	hasVectorPostprocessorByName (const VectorPostprocessorName &name, const std::string &vector_name) const

bool	hasVectorPostprocessorByName (const VectorPostprocessorName &name) const

const VectorPostprocessorName &	getVectorPostprocessorName (const std::string &param_name) const

DenseMatrix< Real >	getGlobalSamples ()

DenseMatrix< Real >	getGlobalSamples ()

DenseMatrix< Real >	getLocalSamples ()

DenseMatrix< Real >	getLocalSamples ()

dof_id_type	getLocalRowBegin () const

dof_id_type	getLocalRowBegin () const

dof_id_type	getLocalRowEnd () const

dof_id_type	getLocalRowEnd () const

const Distribution &	getDistribution (const std::string &name) const

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

const Distribution &	getDistribution (const std::string &name) const

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

const Distribution &	getDistributionByName (const DistributionName &name) const

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

const Distribution &	getDistributionByName (const DistributionName &name) const

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

bool	isVectorPostprocessorDistributed (const std::string &param_name) const

bool	isVectorPostprocessorDistributed (const std::string &param_name) const

bool	isVectorPostprocessorDistributedByName (const VectorPostprocessorName &name) const

bool	isVectorPostprocessorDistributedByName (const VectorPostprocessorName &name) const

const Parallel::Communicator &	comm () const

processor_id_type	n_processors () const

processor_id_type	processor_id () const

bool	isImplicit ()

Moose::StateArg	determineState () const

Static Public Member Functions
static InputParameters	validParams ()

Public Attributes
const ConsoleStream	_console

Protected Types
enum	CommMethod

Protected Member Functions
virtual Real	computeSample (dof_id_type row_index, dof_id_type col_index) override
	Return the sample for the given row (the sample index) and column (the parameter index) More...

void	setNumberOfRandomSeeds (std::size_t number)

Real	getRand (unsigned int index=0)

uint32_t	getRandl (unsigned int index, uint32_t lower, uint32_t upper)

virtual LocalRankConfig	constructRankConfig (bool batch_mode) const

PerfID	registerTimedSection (const std::string &section_name, const unsigned int level) const

PerfID	registerTimedSection (const std::string &section_name, const unsigned int level, const std::string &live_message, const bool print_dots=true) const

std::string	timedSectionName (const std::string &section_name) const

virtual void	addVectorPostprocessorDependencyHelper (const VectorPostprocessorName &) const

const ReporterName &	getReporterName (const std::string &param_name) const

virtual void	addReporterDependencyHelper (const ReporterName &)

void	setNumberOfRows (dof_id_type n_rows)

void	setNumberOfRows (dof_id_type n_rows)

void	setNumberOfCols (dof_id_type n_cols)

void	setNumberOfCols (dof_id_type n_cols)

virtual void	sampleSetUp (const SampleMode)

virtual void	sampleSetUp (const SampleMode)

virtual void	sampleTearDown (const SampleMode)

virtual void	sampleTearDown (const SampleMode)

virtual void	computeSampleMatrix (DenseMatrix< Real > &matrix)

virtual void	computeSampleMatrix (DenseMatrix< Real > &matrix)

virtual void	computeLocalSampleMatrix (DenseMatrix< Real > &matrix)

virtual void	computeLocalSampleMatrix (DenseMatrix< Real > &matrix)

virtual void	computeSampleRow (dof_id_type i, std::vector< Real > &data)

virtual void	computeSampleRow (dof_id_type i, std::vector< Real > &data)

virtual void	advanceGenerators (const dof_id_type count)

virtual void	advanceGenerators (const dof_id_type count)

virtual void	advanceGenerator (const unsigned int seed_index, const dof_id_type count)

virtual void	advanceGenerator (const unsigned int seed_index, const dof_id_type count)

void	setAutoAdvanceGenerators (const bool state)

void	setAutoAdvanceGenerators (const bool state)

void	shuffle (std::vector< T > &data, const std::size_t seed_index=0, const CommMethod method=CommMethod::LOCAL)

void	shuffle (std::vector< T > &data, const std::size_t seed_index=0, const CommMethod method=CommMethod::LOCAL)

virtual void	executeSetUp ()

virtual void	executeSetUp ()

virtual void	executeTearDown ()

virtual void	executeTearDown ()

void	saveGeneratorState ()

void	saveGeneratorState ()

void	restoreGeneratorState ()

void	restoreGeneratorState ()

const T &	getReporterValue (const std::string &param_name, const std::size_t time_index=0)

const T &	getReporterValue (const std::string &param_name, ReporterMode mode, const std::size_t time_index=0)

const T &	getReporterValue (const std::string &param_name, const std::size_t time_index=0)

const T &	getReporterValue (const std::string &param_name, ReporterMode mode, const std::size_t time_index=0)

const T &	getReporterValueByName (const ReporterName &reporter_name, const std::size_t time_index=0)

const T &	getReporterValueByName (const ReporterName &reporter_name, ReporterMode mode, const std::size_t time_index=0)

const T &	getReporterValueByName (const ReporterName &reporter_name, const std::size_t time_index=0)

const T &	getReporterValueByName (const ReporterName &reporter_name, ReporterMode mode, const std::size_t time_index=0)

bool	hasReporterValue (const std::string &param_name) const

bool	hasReporterValue (const std::string &param_name) const

bool	hasReporterValue (const std::string &param_name) const

bool	hasReporterValue (const std::string &param_name) const

bool	hasReporterValueByName (const ReporterName &reporter_name) const

bool	hasReporterValueByName (const ReporterName &reporter_name) const

bool	hasReporterValueByName (const ReporterName &reporter_name) const

bool	hasReporterValueByName (const ReporterName &reporter_name) const

Protected Attributes
std::vector< const Distribution * >	_distributions
	Storage for distribution objects to be utilized. More...

const std::vector< Real > &	_proposal_std
	The proposal distribution standard deviations. More...

const std::vector< Real > &	_initial_values
	Initial values values vector to start the importance sampler. More...

const Real &	_output_limit
	The output limit, exceedance of which indicates failure. More...

const int &	_num_samples_train
	Number of samples to train the importance sampler. More...

const int &	_num_importance_sampling_steps
	Number of importance sampling steps (after the importance distribution has been trained) More...

const Real &	_std_factor
	Factor to be multiplied to the standard deviation of the proposal distribution. More...

const bool &	_use_absolute_value
	Absolute value of the model result. Use this when failure is defined as a non-exceedance rather than an exceedance. More...

const unsigned int &	_num_random_seeds
	Initialize a certain number of random seeds. Change from the default only if you have to. More...

bool	_is_sampling_completed
	True if the sampling is completed. More...

	NONE

	LOCAL

	SEMI_LOCAL

const dof_id_type	_min_procs_per_row

const dof_id_type	_max_procs_per_row

libMesh::Parallel::Communicator	_local_comm

const bool &	_enabled

MooseApp &	_app

const std::string	_type

const std::string	_name

const InputParameters &	_pars

Factory &	_factory

ActionFactory &	_action_factory

const ExecFlagEnum &	_execute_enum

const ExecFlagType &	_current_execute_flag

MooseApp &	_pg_moose_app

const std::string	_prefix

const Parallel::Communicator &	_communicator

const InputParameters &	_ti_params

FEProblemBase &	_ti_feproblem

bool	_is_implicit

Real &	_t

const Real &	_t_old

int &	_t_step

Real &	_dt

Real &	_dt_old

bool	_is_transient

Private Attributes
const std::vector< std::vector< Real > > &	_inputs
	Storage for the inputs vector obtained from the reporter. More...

int	_check_step
	Ensure that the MCMC algorithm proceeds in a sequential fashion. More...

std::vector< Real >	_prev_value
	For proposing the next sample in the MCMC algorithm. More...

std::vector< Real >	_mean_sto
	Storage for means of input values for proposing the next sample. More...

std::vector< Real >	_std_sto
	Storage for standard deviations of input values for proposing the next sample. More...

std::vector< std::vector< Real > >	_inputs_sto
	Storage for previously accepted samples by the decision reporter system. More...

int	_retraining_steps
	Number of retraining performed. More...

const std::vector< bool > *const	_gp_flag
	Indicate whether GP prediction is good or bad to influence next proposed sample. More...

Detailed Description

A class used to perform Adaptive Importance Sampling using a Markov Chain Monte Carlo algorithm.

Definition at line 18 of file AdaptiveImportanceSampler.h.

Constructor & Destructor Documentation

◆ AdaptiveImportanceSampler()

AdaptiveImportanceSampler::AdaptiveImportanceSampler ( const InputParameters & parameters )

Definition at line 53 of file AdaptiveImportanceSampler.C.

   : Sampler(parameters),
     TransientInterface(this),
     _proposal_std(getParam<std::vector<Real>>("proposal_std")),
     _initial_values(getParam<std::vector<Real>>("initial_values")),
     _output_limit(getParam<Real>("output_limit")),
     _num_samples_train(getParam<int>("num_samples_train")),
     _num_importance_sampling_steps(getParam<int>("num_importance_sampling_steps")),
     _std_factor(getParam<Real>("std_factor")),
     _use_absolute_value(getParam<bool>("use_absolute_value")),
     _num_random_seeds(getParam<unsigned int>("num_random_seeds")),
     _is_sampling_completed(false),
     _inputs(getReporterValue<std::vector<std::vector<Real>>>("inputs_reporter")),
     _retraining_steps(0),
     _gp_flag(isParamValid("flag_sample") ? &getReporterValue<std::vector<bool>>("flag_sample")
                                          : nullptr)
 {
   // Filling the `distributions` vector with the user-provided distributions.
   for (const DistributionName & name : getParam<std::vector<DistributionName>>("distributions"))
     _distributions.push_back(&getDistributionByName(name));
 
   /* Adaptive Importance Sampling (AdaptiveImportanceSampler) relies on a Markov Chain Monte Carlo
      (MCMC) algorithm. As such, in MOOSE, any use of MCMC algorithms requires that the `num_steps`
      parameter in the main App's executioner would control the total number of samples. Therefore,
      the `num_rows` parameter typically used by exisiting non-MCMC samplers to set the total number
      of samples has no use here and is fixed to 1.*/
   setNumberOfRows(1);
 
   // Setting the number of columns in the sampler matrix (equal to the number of distributions).
   setNumberOfCols(_distributions.size());
 
   /* `inputs_sto` is a member variable that aids in forming the importance distribution.
      One dimension of this variable is equal to the number of distributions. The other dimension
      of the variable, at the last step, is equal to the number of samples the user desires.*/
   _inputs_sto.resize(_distributions.size());
 
   // Mapping all the input distributions to a standard normal space
   for (unsigned int i = 0; i < _distributions.size(); ++i)
     _inputs_sto[i].push_back(Normal::quantile(_distributions[i]->cdf(_initial_values[i]), 0, 1));
 
   /* `prev_value` is a member variable for tracking the previously accepted samples in the
      MCMC algorithm and proposing the next sample.*/
   _prev_value.resize(_distributions.size());
 
   // `check_step` is a member variable for ensuring that the MCMC algorithm proceeds in a sequential
   // fashion.
   _check_step = 0;
 
   // Storage for means of input values for proposing the next sample
   _mean_sto.resize(_distributions.size());
 
   // Storage for standard deviations of input values for proposing the next sample
   _std_sto.resize(_distributions.size());
 
   setNumberOfRandomSeeds(_num_random_seeds);
 }

Member Function Documentation

◆ computeSample()

Real AdaptiveImportanceSampler::computeSample	(	dof_id_type	row_index,
		dof_id_type	col_index
	)

overrideprotectedvirtual

Return the sample for the given row (the sample index) and column (the parameter index)

Implements Sampler.

Definition at line 111 of file AdaptiveImportanceSampler.C.

 {
   const bool sample = _t_step > 1 && col_index == 0 && _check_step != _t_step;
   const bool gp_flag = _gp_flag ? (*_gp_flag)[0] : false;
 
   if (sample && _is_sampling_completed)
     mooseError("Internal bug: the adaptive sampling is supposed to be completed but another sample "
                "has been requested.");
 
   if (_t_step <= _num_samples_train)
   {
     /* This is the importance distribution training step. Markov Chains are set up
       to sample from the importance region or the failure region using the Metropolis
       algorithm. Given that the previous sample resulted in a model failure, the next
       sample is proposed such that it is very likely to result in a model failure as well.
       The `initial_values` and `proposal_std` parameters provided by the user affects the
       formation of the importance distribution. */
     if (sample && !gp_flag)
     {
       for (dof_id_type j = 0; j < _distributions.size(); ++j)
         _prev_value[j] = Normal::quantile(_distributions[j]->cdf(_inputs[j][0]), 0.0, 1.0);
       Real acceptance_ratio = 0.0;
       for (dof_id_type i = 0; i < _distributions.size(); ++i)
         acceptance_ratio += std::log(Normal::pdf(_prev_value[i], 0.0, 1.0)) -
                             std::log(Normal::pdf(_inputs_sto[i].back(), 0.0, 1.0));
       if (acceptance_ratio > std::log(getRand(_t_step)))
       {
         for (dof_id_type i = 0; i < _distributions.size(); ++i)
           _inputs_sto[i].push_back(_prev_value[i]);
       }
       else
       {
         for (dof_id_type i = 0; i < _distributions.size(); ++i)
           _inputs_sto[i].push_back(_inputs_sto[i].back());
       }
       for (dof_id_type i = 0; i < _distributions.size(); ++i)
         _prev_value[i] =
             Normal::quantile(getRand(_t_step), _inputs_sto[i].back(), _proposal_std[i]);
     }
   }
   else if (sample && !gp_flag)
   {
     /* This is the importance sampling step using the importance distribution created
       in the previous step. Once the importance distribution is known, sampling from
       it is similar to a regular Monte Carlo sampling. */
     for (dof_id_type i = 0; i < _distributions.size(); ++i)
     {
       if (_t_step == _num_samples_train + 1)
       {
         _mean_sto[i] = AdaptiveMonteCarloUtils::computeMean(_inputs_sto[i], 1);
         _std_sto[i] = AdaptiveMonteCarloUtils::computeSTD(_inputs_sto[i], 1);
       }
       _prev_value[i] =
           (Normal::quantile(getRand(_t_step), _mean_sto[i], _std_factor * _std_sto[i]));
     }
 
     // check if we have performed all the importance sampling steps
     if (_t_step >= _num_samples_train + _num_importance_sampling_steps + _retraining_steps)
       _is_sampling_completed = true;
   }
 
   // When the GP fails, the current time step is 'wasted' and the retraining step doesn't
   // happen until the next time step. Therefore, keep track of the number of retraining steps
   // to increase the total number of steps taken.
   if (sample && gp_flag && _t_step > _num_samples_train)
     ++_retraining_steps;
 
   _check_step = _t_step;
   return _distributions[col_index]->quantile(Normal::cdf(_prev_value[col_index], 0.0, 1.0));
 }

◆ getDistributionNames()

const std::vector<const Distribution *>& AdaptiveImportanceSampler::getDistributionNames ( ) const

inline

Definition at line 44 of file AdaptiveImportanceSampler.h.

Referenced by AdaptiveImportanceStats::AdaptiveImportanceStats().

44 { return _distributions; }

AdaptiveImportanceSampler::_distributions

std::vector< const Distribution * > _distributions

Storage for distribution objects to be utilized.

Definition: AdaptiveImportanceSampler.h:59

◆ getImportanceVectorMean()

const std::vector<Real>& AdaptiveImportanceSampler::getImportanceVectorMean ( ) const

inline

Definition at line 38 of file AdaptiveImportanceSampler.h.

Referenced by AdaptiveImportanceStats::execute().

38 { return _mean_sto; }

AdaptiveImportanceSampler::_mean_sto

std::vector< Real > _mean_sto

Storage for means of input values for proposing the next sample.

Definition: AdaptiveImportanceSampler.h:99

◆ getImportanceVectorStd()

const std::vector<Real>& AdaptiveImportanceSampler::getImportanceVectorStd ( ) const

inline

Definition at line 41 of file AdaptiveImportanceSampler.h.

Referenced by AdaptiveImportanceStats::execute().

41 { return _std_sto; }

AdaptiveImportanceSampler::_std_sto

std::vector< Real > _std_sto

Storage for standard deviations of input values for proposing the next sample.

Definition: AdaptiveImportanceSampler.h:102

◆ getInitialValues()

const std::vector<Real>& AdaptiveImportanceSampler::getInitialValues ( ) const

inline

Definition at line 26 of file AdaptiveImportanceSampler.h.

Referenced by AdaptiveMonteCarloDecision::AdaptiveMonteCarloDecision(), and AdaptiveMonteCarloDecision::reinitChain().

26 { return _initial_values; }

AdaptiveImportanceSampler::_initial_values

const std::vector< Real > & _initial_values

Initial values values vector to start the importance sampler.

Definition: AdaptiveImportanceSampler.h:65

◆ getNumSamplesTrain()

const int& AdaptiveImportanceSampler::getNumSamplesTrain ( ) const

inline

Definition at line 29 of file AdaptiveImportanceSampler.h.

Referenced by AdaptiveImportanceStats::execute(), and AdaptiveMonteCarloDecision::execute().

29 { return _num_samples_train; }

AdaptiveImportanceSampler::_num_samples_train

const int & _num_samples_train

Number of samples to train the importance sampler.

Definition: AdaptiveImportanceSampler.h:71

◆ getOutputLimit()

const Real& AdaptiveImportanceSampler::getOutputLimit ( ) const

inline

Definition at line 35 of file AdaptiveImportanceSampler.h.

Referenced by AdaptiveMonteCarloDecision::AdaptiveMonteCarloDecision(), and AdaptiveImportanceStats::execute().

35 { return _output_limit; }

AdaptiveImportanceSampler::_output_limit

const Real & _output_limit

The output limit, exceedance of which indicates failure.

Definition: AdaptiveImportanceSampler.h:68

◆ getStdFactor()

const Real& AdaptiveImportanceSampler::getStdFactor ( ) const

inline

Definition at line 47 of file AdaptiveImportanceSampler.h.

Referenced by AdaptiveImportanceStats::AdaptiveImportanceStats().

47 { return _std_factor; }

AdaptiveImportanceSampler::_std_factor

const Real & _std_factor

Factor to be multiplied to the standard deviation of the proposal distribution.

Definition: AdaptiveImportanceSampler.h:77

◆ getUseAbsoluteValue()

const bool& AdaptiveImportanceSampler::getUseAbsoluteValue ( ) const

inline

Definition at line 32 of file AdaptiveImportanceSampler.h.

Referenced by AdaptiveImportanceStats::execute(), and AdaptiveMonteCarloDecision::execute().

32 { return _use_absolute_value; }

AdaptiveImportanceSampler::_use_absolute_value

const bool & _use_absolute_value

Absolute value of the model result. Use this when failure is defined as a non-exceedance rather than ...

Definition: AdaptiveImportanceSampler.h:80

◆ isAdaptiveSamplingCompleted()

virtual bool AdaptiveImportanceSampler::isAdaptiveSamplingCompleted ( ) const

inlineoverridevirtual

Returns true if the adaptive sampling is completed.

Reimplemented from Sampler.

Definition at line 52 of file AdaptiveImportanceSampler.h.

52 { return _is_sampling_completed; }

AdaptiveImportanceSampler::_is_sampling_completed

bool _is_sampling_completed

True if the sampling is completed.

Definition: AdaptiveImportanceSampler.h:86

◆ validParams()

InputParameters AdaptiveImportanceSampler::validParams ( )

static

Definition at line 19 of file AdaptiveImportanceSampler.C.

Referenced by AISActiveLearning::validParams().

 {
   InputParameters params = Sampler::validParams();
   params.addClassDescription("Adaptive Importance Sampler.");
   params.addRequiredParam<std::vector<DistributionName>>(
       "distributions",
       "The distribution names to be sampled, the number of distributions provided defines the "
       "number of columns per matrix.");
   params.addRequiredParam<ReporterName>("inputs_reporter", "Reporter with input parameters.");
   params.addRequiredParam<std::vector<Real>>("proposal_std",
                                              "Standard deviations of the proposal distributions");
   params.addRequiredParam<Real>("output_limit", "Limiting values of the VPPs");
   params.addRequiredParam<std::vector<Real>>(
       "initial_values", "Initial input values to get the importance sampler started");
   params.addRequiredRangeCheckedParam<int>(
       "num_samples_train",
       "num_samples_train>0",
       "Number of samples to learn the importance distribution");
   params.addRequiredRangeCheckedParam<int>(
       "num_importance_sampling_steps",
       "num_importance_sampling_steps>0",
       "Number of importance sampling steps (after the importance distribution has been trained)");
   params.addRequiredParam<Real>(
       "std_factor", "Factor to be multiplied to the standard deviation of the importance samples");
   params.addParam<bool>("use_absolute_value", false, "Use absolute value of the sub app output");
   params.addParam<unsigned int>(
       "num_random_seeds",
       100000,
       "Initialize a certain number of random seeds. Change from the default only if you have to.");
   params.addParam<ReporterName>("flag_sample",
                                 "Flag samples if the surrogate prediction was inadequate.");
   return params;
 }