Convergence rate and averaging of nonlinear two-time-scale stochastic approximation algo\-rithms

DOI10.1214/105051606000000448zbMath1104.62095arXivmath/0610329OpenAlexW4307708340MaRDI QIDQ862224

Abdelkader Mokkadem, Mariane Pelletier

Publication date: 5 February 2007

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

Full work available at URL: https://arxiv.org/abs/math/0610329

zbMATH Keywords

averaging principletwo-time-scales

Mathematics Subject Classification ID

Central limit and other weak theorems (60F05) Stochastic approximation (62L20)

Related Items

Recursive regression estimation based on the two-time-scale stochastic approximation method and Bernstein polynomials, A Two-Timescale Stochastic Algorithm Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-Critic, Generalized rescaled Pólya urn and its statistical application, On-Line Expectation–Maximization Algorithm for latent Data Models, Optimal Transport-Based Distributionally Robust Optimization: Structural Properties and Iterative Schemes, Risk-Sensitive Reinforcement Learning via Policy Gradient Search, Two-time-scale nonparametric recursive regression estimator for independent functional data, A Two-Time-Scale Stochastic Optimization Framework with Applications in Control and Reinforcement Learning, Two-timescale stochastic gradient descent in continuous time with applications to joint online parameter estimation and optimal sensor placement, Weak convergence of dynamical systems in two timescales, Stochastic global stability and bifurcation of a hydro-turbine generator, Non asymptotic controls on a recursive superquantile approximation, Fast estimation of the median covariation matrix with application to online robust principal components analysis, Stochastic approximation algorithms for superquantiles estimation, Interacting reinforced stochastic processes: statistical inference based on the weighted empirical means, Computing VaR and CVaR using stochastic approximation and adaptive unconstrained importance sampling, Networks of reinforced stochastic processes: asymptotics for the empirical means, Finite-Time Analysis and Restarting Scheme for Linear Two-Time-Scale Stochastic Approximation

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• New method of stochastic approximation type
• Stochastic approximation methods for constrained and unconstrained systems
• Strong convergence of a stochastic approximation algorithm
• Stochastic approximation with two time scales
• On the almost sure asymptotic behaviour of stochastic algorithm
• Convergence rate of linear two-time-scale stochastic approximation.
• Stochastic algorithms
• Weighted means of processes in stochastic approximation
• A companion for the Kiefer-Wolfowitz-Blum stochastic approximation algorithm
• Stochastic Approximation with Averaging of the Iterates: Optimal Asymptotic Rate of Convergence for General Processes
• Matrix Analysis
• On extensions of Polyak's averaging approach to stochastic approximation
• Acceleration of Stochastic Approximation by Averaging
• Stochastic optimization with averaging of trajectories
• Weighted Means in Stochastic Approximation of Minima
• OnActor-Critic Algorithms
• Asymptotic Almost Sure Efficiency of Averaged Stochastic Algorithms
• The Compact Law of the Iterated Logarithm for Multivariate Stochastic Approximation Algorithms
• Actor-Critic--Type Learning Algorithms for Markov Decision Processes