Abstract
Gibbs sampling is a Markov Chain Monte Carlo (MCMC) method often used in Bayesian learning. MCMC methods can be difficult to deploy on parallel and distributed systems due to their inherently sequential nature. We study asynchronous Gibbs sampling, which achieves parallelism by simply ignoring sequential requirements. This method has been shown to produce good empirical results for some hierarchical models, and is popular in the topic modeling community, but was also shown to diverge for other targets. We introduce a theoretical framework for analyzing asynchronous Gibbs sampling and other extensions of MCMC that do not possess the Markov property. We prove that asynchronous Gibbs can be modified so that it converges under appropriate regularity conditions - we call this the exact asynchronous Gibbs algorithm. We study asynchronous Gibbs on a set of examples by comparing the exact and approximate algorithms, including two where it works well, and one where it fails dramatically. We conclude with a set of heuristics to describe settings where the algorithm can be effectively used.
Original language | English |
---|---|
Title of host publication | Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics |
Editors | Neil Lawrence, Mark Reid |
Place of Publication | USA |
Publisher | Society for Artificial Intelligence and Statistics |
Pages | 144-154 |
Number of pages | 11 |
Publication status | Published - 2020 |
Externally published | Yes |
Event | International Conference on Artificial Intelligence and Statistics 2020 - Virtual, Italy Duration: 3 Jun 2020 → 5 Jun 2020 Conference number: 23rd https://www.aistats.org/ (Website) http://proceedings.mlr.press/v108/ (Proceedings) |
Publication series
Name | Proceedings of Machine Learning Research |
---|---|
ISSN (Electronic) | 2640-3498 |
Conference
Conference | International Conference on Artificial Intelligence and Statistics 2020 |
---|---|
Abbreviated title | AISTATS 2020 |
Country/Territory | Italy |
City | Virtual |
Period | 3/06/20 → 5/06/20 |
Internet address |
|