On the stability of some controlled Markov chains and its applications to stochastic approximation with Markovian dynamic

DOI10.1214/13-AAP953zbMath1317.65004arXiv1205.4181OpenAlexW3102716280WikidataQ109998344 ScholiaQ109998344MaRDI QIDQ2258523

Vladislav B. Tadić, Christophe Andrieu, Matti Vihola

Publication date: 26 February 2015

Published in: The Annals of Applied Probability (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1205.4181

zbMATH Keywords

stabilityRobbins-Monro stochastic approximationadaptive Markov chain Monte Carlo algorithmscontrolled Markov ChainLyaunov functionreccurent Markov Chain

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Monte Carlo methods (65C05) Discrete-time Markov processes on general state spaces (60J05) Numerical analysis or methods applied to Markov chains (65C40)

Related Items (5)

Markovian stochastic approximation with expanding projections ⋮ Convergence of Markovian Stochastic Approximation with Discontinuous Dynamics ⋮ Bayesian computation: a summary of the current state, and samples backwards and forwards ⋮ Empirical measure large deviations for reinforced chains on finite spaces ⋮ Stability estimation of some Markov controlled processes

Cites Work

• Unnamed Item
• Adaptive proposal distribution for random walk Metropolis algorithm
• Limit theorems for some adaptive MCMC algorithms with subgeometric kernels
• On the ergodicity of the adaptive Metropolis algorithm on unbounded domains
• On the stability and ergodicity of adaptive scaling Metropolis algorithms
• Markov chains and stochastic stability
• On adaptive Markov chain Monte Carlo algorithms
• On the ergodicity properties of some adaptive MCMC algorithms
• Geometric ergodicity of Metropolis algorithms
• Markovian stochastic approximation with expanding projections
• On the convergence of markovian stochastic algorithms with rapidly decreasing ergodicity rates
• Accelerated Stochastic Approximation
• Stability of Stochastic Approximation under Verifiable Conditions
• An adaptive Metropolis algorithm

This page was built for publication: On the stability of some controlled Markov chains and its applications to stochastic approximation with Markovian dynamic