Central limit theorems for stochastic approximation with controlled Markov chain dynamics

DOI10.1051/ps/2014013zbMath1333.60029arXiv1309.3116OpenAlexW1988545057MaRDI QIDQ2786468

Gersende Fort

Publication date: 12 February 2016

Published in: ESAIM: Probability and Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1309.3116

zbMATH Keywords

stochastic approximationcentral limit theoremscontrolled Markov chains

Mathematics Subject Classification ID

Central limit and other weak theorems (60F05) Discrete-time Markov processes on general state spaces (60J05) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Stochastic approximation (62L20)

Related Items (10)

Generalized rescaled Pólya urn and its statistical application ⋮ Convergence and efficiency of adaptive importance sampling techniques with partial biasing ⋮ Optimal non-asymptotic analysis of the Ruppert-Polyak averaging stochastic algorithm ⋮ Interacting nonlinear reinforced stochastic processes: Synchronization or non-synchronization ⋮ Fluctuations of the empirical measure of freezing Markov chains ⋮ Self-healing umbrella sampling: convergence and efficiency ⋮ Concentration inequalities for additive functionals: a martingale approach ⋮ Stochastic approximation schemes for economic capital and risk margin computations ⋮ Convergence of the Wang-Landau algorithm ⋮ Empirical measure large deviations for reinforced chains on finite spaces

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Convergence of adaptive and interacting Markov chain Monte Carlo algorithms
• Stochastic approximation. A dynamical systems viewpoint.
• Convergence and robustness of the Robbins-Monro algorithm truncated at randomly varying bounds
• Approximation gaussienne d'algorithmes stochastiques à dynamique markovienne. (Gaussian approximation of stochastic algorithms)
• On asymptotically efficient recursive estimation
• Weak convergence rates for stochastic approximation with application to multiple targets and simulated annealing
• Convergence of a stochastic approximation version of the EM algorithm
• Markov chains and invariant probabilities
• Stochastic approximation and its applications
• Stochastic algorithms
• Asymptotic normality for a vector stochastic difference equation with applications in stochastic approximation
• Quantitative Convergence Rates for Subgeometric Markov Chains
• Markov Chains and Stochastic Stability
• Rates of Convergence for Stochastic Approximation Type Algorithms
• Acceleration of Stochastic Approximation by Averaging
• Rate of Convergence for Constrained Stochastic Approximation Algorithms
• Convergence of the Wang-Landau algorithm
• Stability of Stochastic Approximation under Verifiable Conditions
• Performance of a Distributed Stochastic Approximation Algorithm
• Asymptotic normality of randomly truncated stochastic algorithms

This page was built for publication: Central limit theorems for stochastic approximation with controlled Markov chain dynamics