The Zig-Zag Process and Super-Efficient Sampling for Bayesian Analysis of Big Data

Bierkens, Joris and Fearnhead, Paul and Roberts, Gareth (2019) The Zig-Zag Process and Super-Efficient Sampling for Bayesian Analysis of Big Data. Annals of Statistics, 47 (3). pp. 1288-1320. ISSN 0090-5364

[img]
Preview
PDF (zigzagRev4)
zigzagRev4.pdf - Accepted Version
Available under License Creative Commons Attribution.

Download (933kB)

Abstract

Standard MCMC methods can scale poorly to big data settings due to the need to evaluate the likelihood at each iteration. There have been a number of approximate MCMC algorithms that use sub-sampling ideas to reduce this computational burden, but with the drawback that these algorithms no longer target the true posterior distribution. We introduce a new family of Monte Carlo methods based upon a multi-dimensional version of the Zig-Zag process of Bierkens and Roberts (2015), a continuous time piecewise deterministic Markov process. While traditional MCMC methods are reversible by construction (a property which is known to inhibit rapid convergence) the Zig-Zag process offers a flexible non-reversible alternative which we observe to often have favourable convergence properties. We show how the Zig-Zag process can be simulated without discretisation error, and give conditions for the process to be ergodic. Most importantly, we introduce a sub-sampling version of the Zig-Zag process that is an example of an exact approximate scheme, i.e. the resulting approximate process still has the posterior as its stationary distribution. Furthermore, if we use a control-variate idea to reduce the variance of our unbiased estimator, then the Zig-Zag process can be super-efficient: after an initial pre-processing step, essentially independent samples from the posterior distribution are obtained at a computational cost which does not depend on the size of the data.

Item Type:
Journal Article
Journal or Publication Title:
Annals of Statistics
Uncontrolled Keywords:
/dk/atira/pure/subjectarea/asjc/1800/1804
Subjects:
ID Code:
80426
Deposited By:
Deposited On:
21 Jul 2016 15:36
Refereed?:
Yes
Published?:
Published
Last Modified:
31 Oct 2020 04:20