Proceedings Abstracts of the Twenty-Fourth International Joint Conference on Artificial Intelligence

Firefly Monte Carlo: Exact MCMC with Subsets of Data / 4289
Dougal Maclaurin, Ryan Prescott Adams

Markov chain Monte Carlo (MCMC) is a popular tool for Bayesian inference.However, MCMC cannot be practically applied to large data sets because of theprohibitive cost of evaluating every likelihood term at every iteration. Here we present Firefly Monte Carlo (FlyMC) MCMC algorithm with auxiliary variables that only queries the likelihoods of a subset of the data at each iteration yet simulates from the exact posterior distribution. FlyMC is compatible with 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 regularMCMC, allowing MCMC methods to tackle larger datasets than were previously considered feasible.