https://mooseframework.inl.gov
Loading...
Searching...
No Matches
BayesianActiveLearningSampler.h
Go to the documentation of this file.
1//* This file is part of the MOOSE framework
2//* https://www.mooseframework.org
3//*
4//* All rights reserved, see COPYRIGHT for full restrictions
5//* https://github.com/idaholab/moose/blob/master/COPYRIGHT
6//*
7//* Licensed under LGPL 2.1, please see LICENSE for details
8//* https://www.gnu.org/licenses/lgpl-2.1.html
9
10#pragma once
11
12#include "PMCMCBase.h"
13#include "ReporterInterface.h"
14
20{
21public:
23
25
29 const std::vector<std::vector<Real>> & getSampleTries() const;
30
34 const std::vector<Real> & getVarSampleTries() const;
35
36protected:
37 virtual void proposeSamples() override;
38
40 const std::vector<unsigned int> & _sorted_indices;
41
42private:
44 const unsigned int & _num_tries;
45
47 std::vector<std::vector<Real>> _inputs_test;
48
50 std::vector<Real> _var_test;
51};
Fast Bayesian inference with the parallel active learning (partly inspired from El Gammal et al.
const std::vector< unsigned int > & _sorted_indices
The selected sample indices to evaluate the subApp.
const std::vector< std::vector< Real > > & getSampleTries() const
Return the random samples for the GP to try in the reporter class.
const unsigned int & _num_tries
Number of samples to propose in each iteration (not all are sent for subApp evals)
std::vector< std::vector< Real > > _inputs_test
Storage for all the proposed samples.
const std::vector< Real > & getVarSampleTries() const
Return the random variance samples for the GP to try in the reporter class.
std::vector< Real > _var_test
Storage for all the proposed variances.
virtual void proposeSamples() override
Fill in the _new_samples vector of vectors (happens within sampleSetUp)
const InputParameters & parameters() const
A base class used to perform Parallel Markov Chain Monte Carlo (MCMC) sampling.
Definition PMCMCBase.h:20