Methodology and Computing in Applied Probability

, Volume 8, Issue 2, pp 235–254

An Adaptive Version for the Metropolis Adjusted Langevin Algorithm with a Truncated Drift

Authors

    • Department of Mathematics and StatisticsUniversity of Ottawa
Article

DOI: 10.1007/s11009-006-8550-0

Cite this article as:
Atchadé, Y.F. Methodol Comput Appl Probab (2006) 8: 235. doi:10.1007/s11009-006-8550-0

Abstract

This paper extends some adaptive schemes that have been developed for the Random Walk Metropolis algorithm to more general versions of the Metropolis-Hastings (MH) algorithm, particularly to the Metropolis Adjusted Langevin algorithm of Roberts and Tweedie (1996). Our simulations show that the adaptation drastically improves the performance of such MH algorithms. We study the convergence of the algorithm. Our proves are based on a new approach to the analysis of stochastic approximation algorithms based on mixingales theory.

Keywords

Adaptive Markov Chain Monte CarloLangevin algorithmsMetropolis-Hastings algorithmsStochastic approximation algorithms

AMS 2000 Subject Classification

65C0565C4060J2760J35
Download to read the full article text

Copyright information

© Springer Science + Business Media, LLC 2006