Volume 19, 2007Conference Oxford sur les méthodes de Monte Carlo séquentielles
|Page(s)||1 - 5|
|Published online||30 October 2007|
Convergence of the equi-energy sampler
University of Bristol
2 Imperial College London
3 University of British Columbia
4 University of Nice
In a recent paper 'The equi-energy sampler with applications statistical inference and statistical mechanics' Kou, Zhou & Wong (Ann. Statist., 34, 1581-1619, 2006.) have presented a new stochastic simulation method called the equi-energy (EE) sampler. This technique is designed to simulate from a probability measure π, perhaps only known up to a normalizing constant. The authors demonstrate that the sampler performs well in quite challenging problems but their convergence results (Theorem 2) appear incomplete. This was pointed out, in the discussion of the paper, by Atchadé & Liu (Ann. Statist., 34, 1620-1628, 2006.) who proposed an alternative convergence proof. However, this alternative proof, whilst theoretically correct, does not correspond to the algorithm that is implemented. In this note we consider the difficulties of the proofs as well as pointing out an alternative convergence result established by the authors (Andrieu et al. 2007b).
© EDP Sciences, ESAIM, 2007
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.