Convergence of stochastic algorithms: from the Kushner–Clark theorem to the Lyapounov functional method

DOI10.2307/1428165zbMath0881.62085OpenAlexW4249438002MaRDI QIDQ4332210

Jean-Claude Fort, Gilles Pagès

Publication date: 22 February 1998

Published in: Advances in Applied Probability (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.2307/1428165

zbMATH Keywords

ordinary differential equationsstochastic algorithmsLyapounov functional

Mathematics Subject Classification ID

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

Related Items (14)

Interacting generalized Friedman's urn systems ⋮ Randomized urn models revisited using stochastic approximation ⋮ A space quantization method for numerical integration ⋮ Bridging the gap between constant step size stochastic gradient descent and Markov chains ⋮ Convergence of gradient algorithms for nonconvex \(C^{1+ \alpha}\) cost functions ⋮ Contractivity of a Markov operator on the space of normalised positive distributions ⋮ Average Competitive Learning Vector Quantization ⋮ Online EM algorithm for mixture with application to Internet traffic modeling ⋮ Nonlinear randomized urn models: a stochastic approximation viewpoint ⋮ Performance analysis of LVQ algorithms: a statistical physics approach ⋮ On Recursive Estimation in Incomplete Data Models ⋮ Three Stochastic Versions of the EM Algorithm for Estimating Longitudinal Rasch Model ⋮ Convergence of a stochastic approximation version of the EM algorithm ⋮ Weak convergence rates for stochastic approximation with application to multiple targets and simulated annealing

This page was built for publication: Convergence of stochastic algorithms: from the Kushner–Clark theorem to the Lyapounov functional method