Unbiased Markov Chain Monte Carlo: what, why, and how
Autor: | Atchadé, Yves F., Jacob, Pierre E. |
---|---|
Rok vydání: | 2024 |
Předmět: | |
Druh dokumentu: | Working Paper |
Popis: | 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. Comment: To appear in the second edition of the handbook of MCMC |
Databáze: | arXiv |
Externí odkaz: |