June 10, 2024Open Access

Unbiased Markov Chain Monte Carlo: what, why, and how

Key Points

Key points are not available for this paper at this time.

Abstract

This document presents methods to remove the initialization or burn-in bias from Markov chain Monte Carlo (MCMC) estimates, with consequences on parallel computing, convergence diagnostics and performance assessment. The document is written as an introduction to these methods for MCMC users. Some theoretical results are mentioned, but the focus is on the methodology.

Read Full Paperexternally

Bookmark

View Full Paper

Cite This Study

Atchadé et al. (Mon,) studied this question.

synapsesocial.com/papers/68e6577ab6db6435875e6b16 https://doi.org/https://doi.org/10.48550/arxiv.2406.06851

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

1Unbiased Markov chain quasi-Monte Carlo for Gibbs samplers2024
2An invitation to adaptive Markov chain Monte Carlo convergence theory2024
3The role of Markov chain in Monte Carlo simulation2024 · 1 citations
4Estimating Monte Carlo variance from multiple Markov chains2025 · 1 citations
5Entropy-Based Burn-in Time Analysis and Ranking for (A)MCMC Algorithms in High Dimension2025

Bookmark

View Full Paper