Asymptotic Behavior of a Markovian Stochastic Algorithm with Constant Step

DOI10.1137/S0363012997328610zbMath0954.60057OpenAlexW2058699200MaRDI QIDQ4699132

Jean-Claude Fort, Gilles Pagès

Publication date: 23 November 1999

Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/s0363012997328610

zbMATH Keywords

Markov chainstationary distributionsaddle pointstochastic algorithmgradient descent

Mathematics Subject Classification ID

Stochastic approximation (62L20) Continuous-time Markov processes on discrete state spaces (60J27)

Related Items

Some Limit Properties of Markov Chains Induced by Recursive Stochastic Algorithms ⋮ Sur quelques algorithmes récursifs pour les probabilités numériques ⋮ Unnamed Item ⋮ Constant step stochastic approximations involving differential inclusions: stability, long-run convergence and applications ⋮ Convergence rates of Gibbs measures with degenerate minimum ⋮ Bridging the gap between constant step size stochastic gradient descent and Markov chains ⋮ Modeling and control of data transmission ⋮ Convergence and Dynamical Behavior of the ADAM Algorithm for Nonconvex Stochastic Optimization ⋮ Deterministic approximation of best-response dynamics for the matching pennies game ⋮ Stochastic modelling of thermal effects on a ferromagnetic nano particle