Control Variates for Constrained Variables

Maskell, Simon ORCID: 0000-0003-1917-2913, Zhou, Yifan ORCID: 0000-0002-1477-5777 and Mira, Antonietta (2022) Control Variates for Constrained Variables. IEEE SIGNAL PROCESSING LETTERS, 29. pp. 2333-2337.

Text constrained_zero_mean (clean).pdf - Author Accepted Manuscript Download (231kB) | Preview

Abstract

Numerical Bayesian inference methods typified by Markov chain Monte Carlo generate a set of samples from a probability distribution. When using real-valued samples to approximate the expectation of a random variable, the variance of the resulting estimator, obtained by averaging over those samples, decreases as the number of samples increases. However, it is often useful to reduce the variance without increasing the number of samples. Using control variates is one method to achieve such variance reduction and is applicable in contexts where the random variable is unconstrained. To make it possible to use control variates with constrained variables, this paper proposes the use of a non-linear mapping from an unconstrained space to the constrained space. Results indicate that significant reductions in Monte-Carlo error was achieved with negligible additional computational cost.

Item Type:	Article
Additional Information:	(c) 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
Uncontrolled Keywords:	Constraints, control variates, Markov chain Monte Carlo, variance reduction, zero variance
Depositing User:	Symplectic Admin
Date Deposited:	28 Oct 2022 07:18
Last Modified:	15 Mar 2024 11:33
DOI:	10.1109/LSP.2022.3221347
Related URLs:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3165811