Convergence of the Robbins-Monro method for linear problems in a Banach space

DOI10.1016/0022-247X(89)90235-7MaRDI QIDQ1824970zbMATH OpenOpenAlexFDO

Authors Harro Walk, László Zsidó

Publication date 1989

Published in Journal of Mathematical Analysis and Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/0022-247x(89)90235-7

zbMATH Keywords

almost sure convergenceBanach spacebounded linear operatoriterative solutionrecursive formulaRobbins-Monro method

Mathematics Subject Classification ID

Probability theory on linear topological spaces (60B11) Limit theorems for vector-valued random variables (infinite-dimensional case) (60B12) Stochastic approximation (62L20)

Review text

Consider the equation \(Ax=b\), where b belongs to some Banach space X and A is a bounded linear operator from X into itself. It has been noticed by several people under different restrictions that in order to obtain an iterative solution one can use the Robbins-Monro method. The recursive formula is given by \(x_{n+1}=x_ n-\alpha_ n\quad (A_ nx_ n-b_ n),\) common assumptions are \(\alpha_ n\to 0,\) \(\sum \alpha_ n=\infty\) and the weighted means of \(A_ n\) and \(b_ n\) converge to A and b, respectively. The aim of the authors is to give a unified treatment of the convergence of \((x_ n)\) to a solution of \(Ax=b\) under mild conditions.

Recommendations

• The averaged Robbins-Monro method for linear problems in a Banach space
• Convergence analysis of a monotone projection algorithm in reflexive Banach spaces
• scientific article; zbMATH DE number 4050866
• Convergence of mean iterations for nonlinear monotone equations in a Banach space
• Strong Convergence of New Algorithm for Monotone Operator in Banach Spaces
• Monotone convergence of iterative methods for singular linear systems
• Strong convergence analysis of a monotone projection algorithm in a Banach space
• Convergence results of forward-backward algorithms for sum of monotone operators in Banach spaces
• Convergence of two simple methods for solving monotone inclusion problems in reflexive Banach spaces
• Convergence of Broyden’s Method in Banach Spaces

Cites work

• Analysis of stochastic gradient algorithms for linear regression problems
• Applications of a Kushner and Clark lemma to general classes of stochastic algorithms
• Convergence of an adaptive linear estimation algorithm
• scientific article; zbMATH DE number 3833142 (Why is no real title available?)
• scientific article; zbMATH DE number 3940520 (Why is no real title available?)
• scientific article; zbMATH DE number 4094620 (Why is no real title available?)
• scientific article; zbMATH DE number 3653234 (Why is no real title available?)
• scientific article; zbMATH DE number 3721550 (Why is no real title available?)
• scientific article; zbMATH DE number 3469556 (Why is no real title available?)
• scientific article; zbMATH DE number 3530849 (Why is no real title available?)
• scientific article; zbMATH DE number 3438157 (Why is no real title available?)
• scientific article; zbMATH DE number 3449064 (Why is no real title available?)
• scientific article; zbMATH DE number 3278065 (Why is no real title available?)
• scientific article; zbMATH DE number 3306842 (Why is no real title available?)
• scientific article; zbMATH DE number 3317198 (Why is no real title available?)
• scientific article; zbMATH DE number 3344968 (Why is no real title available?)
• scientific article; zbMATH DE number 3049368 (Why is no real title available?)
• Lernprozesse mit zeitabhängigen Wahrscheinlichkeiten
• Matrixtransformationen von Folgenräumen. Eine Ergebnisübersicht
• Spectral and ergodic properties of the analytic generators
• Stochastic approximation from ergodic sample for linear regression
• The Norm of a Hermitian Element in a Banach Algebra

Cited in

(12)

• Rate of convergence of stochastic approximation procedures in a Banach space
• Convergence from below of the modified Robbins-Monro procedure
• On the asymptotic behaviour of linear learning processes with partial forgetting
• An almost sure invariance principle for stochastic approximation procedures in linear filtering theory
• Weighted averaging and stochastic approximation
• Distribution-free robust linear regression
• The averaged Robbins-Monro method for linear problems in a Banach space
• Recursive estimation: asymptotic confidence regions by empirical quantiles
• Stochastic fictitious play with continuous action sets
• Exact bounds for the rate of convergence in general stochastic approximation procedures
• Estimating structural parameters in regression models with adaptive learning
• Convergence rates and decoupling in linear stochastic approximation algorithms

This page was built for publication: Convergence of the Robbins-Monro method for linear problems in a Banach space

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1824970)