A limit theorem for the Robbins-Monro approximation

DOI10.1007/BF00736010zbMath0253.62046OpenAlexW2076742758MaRDI QIDQ5667394

Pál Révész, Péter Major

Publication date: 1973

Published in: Zeitschrift für Wahrscheinlichkeitstheorie und verwandte Gebiete (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/bf00736010

Mathematics Subject Classification ID

Asymptotic distribution theory in statistics (62E20) Central limit and other weak theorems (60F05) Stochastic approximation (62L20)

Related Items (14)

An estimate for the convergence rate of the Robbins-Monro process ⋮ Asymptotic confidence regions of stochastic approximation procedures in Hilbert spaces ⋮ On the choice of step size in the Robbins-Monro procedure ⋮ Unnamed Item ⋮ Recursive M-estimators of location ⋮ Asymptotically efficient recursive estimation for incomplete data models using the observed information. ⋮ Asymptotic behavior for the Robbins–Monro process ⋮ Parallel and bootstrapped stochastic approximation ⋮ Isotonic estimation in stochastic approximation ⋮ Lower error bounds for the stochastic gradient descent optimization algorithm: sharp convergence rates for slowly and fast decaying learning rates ⋮ Non-asymptotic confidence bounds for stochastic approximation algorithms with constant step size ⋮ Stochastic approximation and the final value theorem ⋮ Asymptotic behaviour of a class of stochastic approximation procedures ⋮ Stochastic approximation models in estimating productivity

Cites Work

• Unnamed Item
• On Dvoretzky Stochastic Approximation Theorems
• On Asymptotic Normality in Stochastic Approximation
• Normal approximation and large deviations for the Robbins-Monro Process
• Asymptotic Distribution of Stochastic Approximation Procedures
• A Stochastic Approximation Method
• Approximation Methods which Converge with Probability one
• On a Stochastic Approximation Method

This page was built for publication: A limit theorem for the Robbins-Monro approximation