griewank_mcmc_sampling.cpp File Reference

Samples a N-dimensional Griewank function. More...

#include "likelihood.h"
#include "sampler_differential_evolution_tempered_MCMC.h"
#include "sampler_differential_evolution_deo_tempered_MCMC.h"
#include <mpi.h>
#include <memory>
#include <string>
Include dependency graph for griewank_mcmc_sampling.cpp:

Functions

int main (int argc, char *argv[])
 

Detailed Description

Author
Roman Gold & Paul Tiede & Mansour Karami
Date
Feb 2020

Testing the ability of the sampler to sample multi-peaked likelihood distributions with long tails. The natural logarithm of the likelihood is given by:

\(\log{(L(\mathbf{x}))} = 1 + 1/4000 \sum_{i=1}^n x_i^2 - \Pi_{i=1}^n cos(x_i/sqrt{i}) \)

Using the output chain file the marginalized distributions are calculated and plotted:

sampler-griewank-triangle.png
Marginalized posterior probabilty distribution