Pseudo-Marginal Slice Sampling

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Markov chain Monte Carlo (MCMC) methods asymptotically sample from complex probability distributions. The pseudo-marginal MCMC framework only requires an unbiased estimator of the unnormalized probability distribution function to construct a Markov chain. However, the resulting chains are harder to tune to a target distribution than conventional MCMC, and the types of updates available are limited. We describe a general way to clamp and update the random numbers used in a pseudo-marginal method’s unbiased estimator. In this framework we can use slice sampling and other adaptive methods.We obtain more robust Markov chains,which often mix more quickly.
Original languageEnglish
Title of host publicationProceedings of the 19th International Conference on Artificial Intelligence and Statistics 2016
Place of PublicationCadiz, Spain
PublisherPMLR
Pages911-919
Number of pages9
Volume51
Publication statusPublished - May 2016
Event19th International Conference on Artificial Intelligence and Statistics - Cadiz, Spain
Duration: 9 May 201611 May 2016
https://www.aistats.org/aistats2016/

Conference

Conference19th International Conference on Artificial Intelligence and Statistics
Abbreviated titleAI and Statistics 2016
CountrySpain
CityCadiz
Period9/05/1611/05/16
Internet address

Fingerprint Dive into the research topics of 'Pseudo-Marginal Slice Sampling'. Together they form a unique fingerprint.

Cite this