Arnaud Doucet

Title: Sequential Monte Carlo Samplers

(joint work with Pierre Del Moral and Gareth W. Peters)

Abstract:

In this talk, we present a general methodology to sample from a sequence of probability distributions defined on a common space; ie in cases where one traditionally uses MCMC . We propose to approximate these distributions by a large set of random samples which evolves over time using simple sampling and resampling mechanisms. This methodology not only yields a whole set of principled algorithms to make parallel Markov chain Monte Carlo runs interact but also provides us with new algorithms for sequential Bayesian estimation and global optimization. This talk is illustrated by several examples arising in Bayesian inference.