Fall Seminar Series  October 22, 2009
University of Minnesota
School of Statistics
College
of Liberal Arts

Hybrid Samplers for Ill-posed Inverse Problems

Radu Herbei
Department of Statistics
  Ohio State University

Thursday, October 22, 2009
3:30 PM, 115 Ford Hall
Minneapolis, East Bank Campus
Social at 3:00 PM, 300 Ford Hall

 

Abstract

In the Bayesian approach to ill-posed inverse problems, regularization is imposed by specifying a prior distribution on the parameters of interest and MCMC samplers are used to extract information about its posterior distribution. In this talk we investigate the convergence properties of the random-scan random walk Metropolis (RSM) algorithm for posterior distributions in ill-posed inverse problems. We provide an accessible set of sufficient conditions, in terms of the observational model and the prior, to ensure geometric ergodicity of RSM samplers of the posterior distribution. We illustrate how these conditions can be checked when estimating the coefficients of a partial differential equation in a Bayesian framework.