On the convergence of stochastic approximations under a subgeometric ergodic Markov dynamic

DOI10.1214/21-EJS1827zbMath1466.60136OpenAlexW3034791360WikidataQ114060467 ScholiaQ114060467MaRDI QIDQ2044347

Stéphanie Allassonnière, Vianney Debavelaere, Stanley Durrleman

Publication date: 9 August 2021

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1214/21-ejs1827

zbMATH Keywords

stochastic approximationsubgeometric ergodicityMarkovian dynamic

Mathematics Subject Classification ID

Discrete-time Markov processes on general state spaces (60J05) Stochastic programming (90C15) Stochastic approximation (62L20)

Cites Work

• Unnamed Item
• Unnamed Item
• Limit theorems for some adaptive MCMC algorithms with subgeometric kernels. II
• Limit theorems for some adaptive MCMC algorithms with subgeometric kernels
• Construction of Bayesian deformable models via a stochastic approximation algorithm: a convergence study
• Maximum likelihood estimation in nonlinear mixed effects models
• Convergence and robustness of the Robbins-Monro algorithm truncated at randomly varying bounds
• \(V\)-subgeometric ergodicity for a Hastings-Metropolis algorithm
• Geometric ergodicity of Metropolis algorithms
• Convergence of a stochastic approximation version of the EM algorithm
• Practical drift conditions for subgeometric rates of convergence.
• Properties of the stochastic approximation EM algorithm with mini-batch sampling
• A stochastic algorithm for probabilistic independent component analysis
• Polynomial ergodicity of Markov transition kernels.
• Bayesian Mixed Effect Atlas Estimation with a Diffeomorphic Deformation Model
• Geometric convergence and central limit theorems for multidimensional Hastings and Metropolis algorithms
• Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
• Stochastic Approximation for Nonexpansive Maps: Application to Q-Learning Algorithms
• Markov Chains
• Coupling a stochastic approximation version of EM with an MCMC procedure
• The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
• Stability of Stochastic Approximation under Verifiable Conditions
• Coupling and Ergodicity of Adaptive Markov Chain Monte Carlo Algorithms
• A Stochastic Approximation Method
• An adaptive Metropolis algorithm