Unbiased Markov Chain Monte Carlo Methods with Couplings
Authors:
Top Cited Papers
Open Access
- 6 May 2020
- journal article
- research article
- Published by Oxford University Press (OUP) in Journal of the Royal Statistical Society Series B: Statistical Methodology
- Vol. 82 (3) , 543-600
Abstract
Summary: Markov chain Monte Carlo (MCMC) methods provide consistent approximations of integrals as the number of iterations goes to ∞. MCMC estimators are generally biased after any fixed number of iterations. We propose to remove this bias by using couplings of Markov chains together with a telescopic sum argument of Glynn and Rhee. The resulting unbiased estimators can be computed independently in parallel. We discuss practical couplings for popular MCMC algorithms. We establish the theoretical validity of the estimators proposed and study their efficiency relative to the underlying MCMC algorithms. Finally, we illustrate the performance and limitations of the method on toy examples, on an Ising model around its critical temperature, on a high dimensional variable-selection problem, and on an approximation of the cut distribution arising in Bayesian inference for models made of multiple modules.Keywords
This publication has 121 references indexed in Scilit:
- Exact sampling for intractable probability distributions via a Bernoulli factoryElectronic Journal of Statistics, 2012
- A general method for debiasing a Monte Carlo estimatorMonte Carlo Methods and Applications, 2011
- Discretization of Continuous Markov Chains and Markov Chain Monte Carlo Convergence AssessmentJournal of the American Statistical Association, 1998
- A Coupling-Regeneration Scheme for Diagnosing Convergence in Markov Chain Monte Carlo AlgorithmsJournal of the American Statistical Association, 1998
- Studying Convergence of Markov Chain Monte Carlo Algorithms Using Coupled Sample PathsJournal of the American Statistical Association, 1996
- Regeneration in Markov Chain SamplersJournal of the American Statistical Association, 1995
- Bayesian Analysis of Binary and Polychotomous Response DataJournal of the American Statistical Association, 1993
- Sampling-Based Approaches to Calculating Marginal DensitiesJournal of the American Statistical Association, 1990
- Hybrid Monte CarloPhysics Letters B, 1987
- Robust Empirical Bayes Analyses of Event RatesTechnometrics, 1987