Mark Huber Publications

Perfect simulation for image restoration
M. Huber, Stochastic Models, vol. 23 no. 3 (August, 2007), pp. 475–487.

Abstract: The coupling method has been an enormously useful tool for studying the mixing time of Markov chains and as the basis of perfect sampling algorithms such as Coupling From the Past. Several methods such as Wilson’s layered multishift coupling and Breyer and Roberts’ catalytic coupling have been introduced to use the coupling approach on continuous state spaces. This work builds upon these approaches by using a simple coupling for small Metropolis moves together with catalytic coupling. As an application, the analysis of a Markov chain for the autonormal distribution in the Wasserstein metric of A. Gibbs is extended to an analysis in total variation distance. Moreover, a perfect sampling algorithm is constructed that has mean running time O (N lnN ) time for fixed values of the parameters of the model.

Keywords: Autonormal model; Coupling; Image analysis; Perfect simulation

2000 Mathematics Subject Classification: Primary 68U20, Secondary 60J27,62M40

This site supported by NSF CAREER grant DMS-05-48153. Last update: 04 December 2009. Note: All downloads provided solely for use within the restrictions of the Fair Use Act, and all copyrights remain with their respective owners.