Semi-Exact Control Functionals From Sard's Method

South, Leah and Karvonen, Toni and Nemeth, Christopher and Girolami, Mark and Oates, Chris J. (2021) Semi-Exact Control Functionals From Sard's Method. Biometrika. ISSN 0006-3444

[img]
Text (Bayes_Sard_Stein)
Bayes_Sard_Stein.pdf - Accepted Version
Available under License Creative Commons Attribution.

Download (479kB)

Abstract

A novel control variate technique is proposed for post-processing of Markov chain Monte Carlo output, based both on Stein's method and an approach to numerical integration due to Sard. The resulting estimators of posterior expected quantities of interest are proven to be polynomially exact in the Gaussian context, while empirical results suggest the estimators approximate a Gaussian cubature method near the Bernstein-von-Mises limit. The main theoretical result establishes a bias-correction property in settings where the Markov chain does not leave the posterior invariant. Empirical results are presented across a selection of Bayesian inference tasks. All methods used in this paper are available in the R package ZVCV.

Item Type:
Journal Article
Journal or Publication Title:
Biometrika
Uncontrolled Keywords:
/dk/atira/pure/subjectarea/asjc/1100/1101
Subjects:
ID Code:
155711
Deposited By:
Deposited On:
03 Jun 2021 11:10
Refereed?:
Yes
Published?:
Published
Last Modified:
27 Nov 2021 06:03