An alternative proof for convergence of stochastic approximation algorithms

DOI10.1109/9.486642zbMATH Open0859.93058OpenAlexW2118825134MaRDI QIDQ4884112FDOQ4884112

Authors:

Publication date: 10 April 1997

Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1109/9.486642

Recommendations

• Almost sure convergence of a class of stochastic algorithms
• Almost sure convergence of stochastic approximation algorithms with non-additive noise
• Stochastic approximation algorithms: Nonasymptotic estimation of their convergence rates
• Convergence of stochastic approximation algorithms under irregular conditions
• Sufficient and necessary condition for the convergence of stochastic approximation algorithms
• Convergence of a class of stochastic approximation procedures
• Generalization of the Dvoretzky theorem of convergence rate of the stochastic approximation algorithms
• On the almost sure convergence of a general stochastic approximation procedure

zbMATH Keywords

convergenceHilbert spacesRobbins-Monro stochastic approximation algorithmsKushner-Clark condition

Mathematics Subject Classification ID

Stochastic approximation (62L20)

Cited In (4)

• Title not available (Why is that?)
• Equivalent necessary and sufficient conditions on noise sequences for stochastic approximation algorithms
• Weighted averaging and stochastic approximation
• Stochastic approximation algorithms: overview and recent trends.

This page was built for publication: An alternative proof for convergence of stochastic approximation algorithms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4884112)