Coupling and Ergodicity of Adaptive Markov Chain Monte Carloalgorithms
نویسندگان
چکیده
Weconsider basic ergodicity properties of adaptiveMarkov chainMonteCarlo algorithms under minimal assumptions, using coupling constructions. We prove convergence in distribution and a weak law of large numbers. We also give counterexamples to demonstrate that the assumptions we make are not redundant.
منابع مشابه
Coupling and Ergodicity of Adaptive MCMC
We consider basic ergodicity properties of adaptive MCMC algorithms under minimal assumptions, using coupling constructions. We prove convergence in distribution and a weak law of large numbers. We also give counter-examples to demonstrate that the assumptions we make are not redundant.
متن کاملOn the Containment Condition for Adaptive Markov Chain Monte Carlo Algorithms
This paper considers ergodicity properties of certain adaptive Markov chain Monte Carlo (MCMC) algorithms for multidimensional target distributions, in particular Adaptive Metropolis and Adaptive Metropoliswithin-Gibbs. It was previously shown by Roberts and Rosenthal (2007) that Diminishing Adaptation and Containment imply ergodicity of adaptive MCMC. We derive various sufficient conditions to...
متن کاملConvergence of Adaptive Markov Chain Monte Carlo Algorithms
In the thesis, we study ergodicity of adaptive Markov Chain Monte Carlo methods (MCMC) based on two conditions (Diminishing Adaptation and Containment which together imply ergodicity), explain the advantages of adaptive MCMC, and apply the theoretical result for some applications. First we show several facts: 1. Diminishing Adaptation alone may not guarantee ergodicity; 2. Containment is not ne...
متن کاملExplicit control of subgeometric ergodicity
This paper discusses explicit quantitative bounds on the convergence rates of Markov chains on general state spaces, under so-called drift and minorization conditions. The focus of this paper is on practical conditions that lead to subgeometric rates. Such explicit bounds are particularly relevant in applications where a family of Markov transition probabilities {Pθ : θ ∈ Θ} is considered and f...
متن کاملCurvature, Concentration and Error Estimates for Markov Chain Monte Carlo by Aldéric Joulin
We provide explicit nonasymptotic estimates for the rate of convergence of empirical means of Markov chains, together with a Gaussian or exponential control on the deviations of empirical means. These estimates hold under a “positive curvature” assumption expressing a kind of metric ergodicity, which generalizes the Ricci curvature from differential geometry and, on finite graphs, amounts to co...
متن کامل