A Note on Convergence of the Equi-Energy Sampler

DOI10.1080/07362990701857178zbMATH Open1214.82098arXiv0711.0164OpenAlexW1972913069MaRDI QIDQ5459757FDOQ5459757

Authors: Christophe Andrieu, Ajay Jasra, Arnaud Doucet, Pierre Del Moral 

Publication date: 29 April 2008

Published in: Stochastic Analysis and Applications (Search for Journal in Brave)

Abstract: In a recent paper `The equi-energy sampler with applications statistical inference and statistical mechanics' [Ann. Stat. 34 (2006) 1581--1619], Kou, Zhou & Wong have presented a new stochastic simulation method called the equi-energy (EE) sampler. This technique is designed to simulate from a probability measure $pi$, 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 Atchad'e & Liu (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 provide a new proof of convergence of the equi-energy sampler based on the Poisson equation and on the theory developed in Andrieu et al. (2007) for emph{Non-Linear} Markov chain Monte Carlo (MCMC). The objective of this note is to provide a proof of correctness of the EE sampler when there is only one feeding chain; the general case requires a much more technical approach than is suitable for a short note. In addition, we also seek to highlight the difficulties associated with the analysis of this type of algorithm and present the main techniques that may be adopted to prove the convergence of it.

Full work available at URL: https://arxiv.org/abs/0711.0164

Recommendations

• Convergence of the equi-energy sampler
• Discussion of ``Equi-energy sampler by Kou, Zhou and Wong
• Adaptive equi-energy sampler: convergence and illustration
• A cautionary tale on the efficiency of some adaptive Monte Carlo schemes
• Equi-energy sampling does not converge rapidly on the mean-field Potts model with three colors close to the critical temperature

zbMATH Keywords

equi-energy samplerPoisson equationuniform ergodicitynonlinear Markov chain Monte Carlo method

Mathematics Subject Classification ID

Bayesian inference (62F15) Monte Carlo methods (65C05) Numerical analysis or methods applied to Markov chains (65C40) Limit theorems in probability theory (60F99)

Cites Work

• Equi-energy sampler with applications in statistical inference and statistical mechanics
• A Liapounov bound for solutions of the Poisson equation
• Non-linear Markov Chain Monte Carlo
• Strong laws for 𝐿- and 𝑢-statistics
• Measure-valued processes and interacting particle systems. Application to nonlinear filtering problems
• Discussion of ``Equi-energy sampler by Kou, Zhou and Wong
• On convergence of chains with occupational self–interactions

Cited In (11)

• Convergence of the equi-energy sampler and its application to the ising model
• A central limit theorem for adaptive and interacting Markov chains
• On the convergence rates of some adaptive Markov chain Monte Carlo algorithms
• Adaptive equi-energy sampler: convergence and illustration
• Convergence of the equi-energy sampler
• Discussion of ``Equi-energy sampler by Kou, Zhou and Wong
• Convergence of adaptive and interacting Markov chain Monte Carlo algorithms
• On nonlinear Markov chain Monte Carlo
• Equi-energy sampler with applications in statistical inference and statistical mechanics
• Parallel tempering with equi-energy moves
• Equi-energy sampling does not converge rapidly on the mean-field Potts model with three colors close to the critical temperature

This page was built for publication: A Note on Convergence of the Equi-Energy Sampler

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5459757)