Optimal Thinning of MCMC Output

arXiv2005.03952MaRDI QIDQ6340297

Jon Cockayne, Lester Mackey, Chris. J. Oates, Marina Riabiz, Pawel Swietach, Steven A. Niederer, Wilson Chen

Publication date: 8 May 2020

Abstract: The use of heuristics to assess the convergence and compress the output of Markov chain Monte Carlo can be sub-optimal in terms of the empirical approximations that are produced. Typically a number of the initial states are attributed to "burn in" and removed, whilst the remainder of the chain is "thinned" if compression is also required. In this paper we consider the problem of retrospectively selecting a subset of states, of fixed cardinality, from the sample path such that the approximation provided by their empirical distribution is close to optimal. A novel method is proposed, based on greedy minimisation of a kernel Stein discrepancy, that is suitable for problems where heavy compression is required. Theoretical results guarantee consistency of the method and its effectiveness is demonstrated in the challenging context of parameter inference for ordinary differential equations. Software is available in the Stein Thinning package in Python, R and MATLAB.

Has companion code repository: https://github.com/wilson-ye-chen/stein_thinning_matlab

This page was built for publication: Optimal Thinning of MCMC Output