Unbiased approximation of posteriors via coupled particle Markov chain Monte Carlo

Willem van den Boom, Ajay Jasra, Maria De Iorio, Alexandros Beskos, Johan G. Eriksson

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

Markov chain Monte Carlo (MCMC) is a powerful methodology for the approximation of posterior distributions. However, the iterative nature of MCMC does not naturally facilitate its use with modern highly parallel computation on HPC and cloud environments. Another concern is the identification of the bias and Monte Carlo error of produced averages. The above have prompted the recent development of fully (‘embarrassingly’) parallel unbiased Monte Carlo methodology based on coupling of MCMC algorithms. A caveat is that formulation of effective coupling is typically not trivial and requires model-specific technical effort. We propose coupling of MCMC chains deriving from sequential Monte Carlo (SMC) by considering adaptive SMC methods in combination with recent advances in unbiased estimation for state-space models. Coupling is then achieved at the SMC level and is, in principle, not problem-specific. The resulting methodology enjoys desirable theoretical properties. A central motivation is to extend unbiased MCMC to more challenging targets compared to the ones typically considered in the relevant literature. We illustrate the effectiveness of the algorithm via application to two complex statistical models: (i) horseshoe regression; (ii) Gaussian graphical models.
Original languageEnglish (US)
JournalSTATISTICS AND COMPUTING
Volume32
Issue number3
DOIs
StatePublished - Apr 23 2022

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Theoretical Computer Science
  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Fingerprint

Dive into the research topics of 'Unbiased approximation of posteriors via coupled particle Markov chain Monte Carlo'. Together they form a unique fingerprint.

Cite this