Studying stellar binary systems with the Laser Interferometer Space Antenna using Delayed Rejection Markov chain Monte Carlo methods

TL;DR

This paper introduces a new Markov chain Monte Carlo algorithm to efficiently analyze complex LISA data sets with multiple local maxima, improving the detection of stellar binary signals.

Contribution

A novel fully Markovian Delayed Rejection MCMC method is developed to better explore challenging likelihood landscapes in gravitational wave data analysis.

Findings

Enhanced sampling efficiency demonstrated on simulated LISA data

Successfully identified known binary signals in noisy data

Outperforms traditional MCMC methods in complex likelihood scenarios

Abstract

Bayesian analysis of LISA data sets based on Markov chain Monte Carlo methods has been shown to be a challenging problem, in part due to the complicated structure of the likelihood function consisting of several isolated local maxima that dramatically reduces the efficiency of the sampling techniques. Here we introduce a new fully Markovian algorithm, a Delayed Rejection Metropolis-Hastings Markov chain Monte Carlo method, to efficiently explore these kind of structures and we demonstrate its performance on selected LISA data sets containing a known number of stellar-mass binary signals embedded in Gaussian stationary noise.