Translator Disclaimer
August 2007 Weak convergence of Metropolis algorithms for non-i.i.d. target distributions
Mylène Bédard
Ann. Appl. Probab. 17(4): 1222-1244 (August 2007). DOI: 10.1214/105051607000000096

Abstract

In this paper, we shall optimize the efficiency of Metropolis algorithms for multidimensional target distributions with scaling terms possibly depending on the dimension. We propose a method for determining the appropriate form for the scaling of the proposal distribution as a function of the dimension, which leads to the proof of an asymptotic diffusion theorem. We show that when there does not exist any component with a scaling term significantly smaller than the others, the asymptotically optimal acceptance rate is the well-known 0.234.

Citation

Download Citation

Mylène Bédard. "Weak convergence of Metropolis algorithms for non-i.i.d. target distributions." Ann. Appl. Probab. 17 (4) 1222 - 1244, August 2007. https://doi.org/10.1214/105051607000000096

Information

Published: August 2007
First available in Project Euclid: 10 August 2007

zbMATH: 1144.60016
MathSciNet: MR2344305
Digital Object Identifier: 10.1214/105051607000000096

Subjects:
Primary: 60F05
Secondary: 65C40

Rights: Copyright © 2007 Institute of Mathematical Statistics

JOURNAL ARTICLE
23 PAGES


SHARE
Vol.17 • No. 4 • August 2007
Back to Top