Metropolis--Hastings with Scalable Subsampling

TL;DR

This paper introduces a subsample Metropolis-Hastings algorithm that maintains exactness and improves computational efficiency for Bayesian inference on large datasets by using control variates and smaller subsamples.

Contribution

It presents a novel subsample MH method that ensures detailed balance and efficiency, outperforming existing algorithms on large-scale Bayesian inference tasks.

Findings

Requires smaller subsamples than standard MH

Achieves higher computational efficiency

Maintains exactness with control variates

Abstract

The Metropolis-Hastings (MH) algorithm is one of the most widely used Markov Chain Monte Carlo schemes for generating samples from Bayesian posterior distributions. The algorithm is asymptotically exact, flexible and easy to implement. However, in the context of Bayesian inference for large datasets, evaluating the likelihood on the full data for thousands of iterations until convergence can be prohibitively expensive. This paper introduces a new subsample MH algorithm that satisfies detailed balance with respect to the target posterior and utilises control variates to enable exact, efficient Bayesian inference on datasets with large numbers of observations. Through theoretical results, simulation experiments and real-world applications on certain generalised linear models, we demonstrate that our method requires substantially smaller subsamples and is computationally more efficient than the standard MH algorithm and other exact subsample MH algorithms.