Firefly Monte Carlo: Exact MCMC with subsets of data

Dougal Maclaurin, Ryan P. Adams

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

48 Scopus citations

Abstract

Markov chain Monte Carlo (MCMC) is a popular and successful general-purpose tool for Bayesian inference. However, MCMC cannot be practically applied to large data sets because of the prohibitive cost of evaluating every likelihood term at every iteration. Here we present Firefly Monte Carlo (FlyMC) an auxiliary variable MCMC algorithm that only queries the likelihoods of a potentially small subset of the data at each iteration yet simulates from the exact posterior distribution, in contrast to recent proposals that are approximate even in the asymptotic limit. FlyMC is compatible with a wide variety of modern MCMC algorithms, and only requires a lower bound on the per-datum likelihood factors. In experiments, we find that FlyMC generates samples from the posterior more than an order of magnitude faster than regular MCMC, opening up MCMC methods to larger datasets than were previously considered feasible.

Original languageEnglish (US)
Title of host publicationUncertainty in Artificial Intelligence - Proceedings of the 30th Conference, UAI 2014
EditorsNevin L. Zhang, Jin Tian
PublisherAUAI Press
Pages543-552
Number of pages10
ISBN (Electronic)9780974903910
StatePublished - Jan 1 2014
Externally publishedYes
Event30th Conference on Uncertainty in Artificial Intelligence, UAI 2014 - Quebec City, Canada
Duration: Jul 23 2014Jul 27 2014

Publication series

NameUncertainty in Artificial Intelligence - Proceedings of the 30th Conference, UAI 2014

Other

Other30th Conference on Uncertainty in Artificial Intelligence, UAI 2014
CountryCanada
CityQuebec City
Period7/23/147/27/14

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Firefly Monte Carlo: Exact MCMC with subsets of data'. Together they form a unique fingerprint.

Cite this