Home > Research > Publications & Outputs > Semi-Exact Control Functionals From Sard's Method

Electronic data

  • Bayes_Sard_Stein

    Rights statement: 12m

    Accepted author manuscript, 468 KB, PDF document

    Embargo ends: 1/01/50

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

View graph of relations

Semi-Exact Control Functionals From Sard's Method

Research output: Contribution to journalJournal articlepeer-review

Forthcoming
Close
<mark>Journal publication date</mark>1/06/2021
<mark>Journal</mark>Biometrika
Publication StatusAccepted/In press
<mark>Original language</mark>English

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.