Non-asymptotic confidence bounds for stochastic approximation algorithms with constant step size

DOI10.1007/BF01301683zbMATH Open0716.62081OpenAlexW2003163868WikidataQ59255200 ScholiaQ59255200MaRDI QIDQ753365FDOQ753365

Authors: Georg Ch. Pflug 

Publication date: 1990

Published in: Monatshefte für Mathematik (Search for Journal in Brave)

Full work available at URL: https://eudml.org/doc/178503

Recommendations

• scientific article; zbMATH DE number 4085419
• A stopped stochastic approximation algorithm
• A stopping rule for the Robbins-Monro method
• Confidence intervals from stochastic approximation
• scientific article; zbMATH DE number 53013

zbMATH Keywords

confidence regionsstopping timecoverage probabilitycomparison resultconstant step-sizeindependent errorsinner products of subsequent gradient estimatesmultidimensional Robbins-Monro procedurenon-asymptotic confidence boundsstationary distribution of Markovian processes

Mathematics Subject Classification ID

Parametric tolerance and confidence regions (62F25) Stochastic approximation (62L20)

Cites Work

• A Newton-Raphson version of the multivariate Robbins-Monro procedure
• Stochastic approximation methods for constrained and unconstrained systems
• A Stochastic Approximation Method
• Title not available (Why is that?)
• Title not available (Why is that?)
• On a new stopping rule for stochastic approximation
• Some Multivariate Chebyshev Inequalities with Extensions to Continuous Parameter Processes
• Title not available (Why is that?)
• Stochastic Minimization with Constant Step-Size: Asymptotic Laws
• COMPARISON OF SOME NON-LINEAR AUTOREGRESSIVE PROCESSES
• Title not available (Why is that?)
• Asymptotic Properties of Stochastic Approximations with Constant Coefficients
• A measure of the tracking capability of recursive stochastic algorithms with constant gains
• Title not available (Why is that?)
• Bounded Length Confidence Intervals for the Zero of a Regression Function
• A limit theorem for the Robbins-Monro approximation

Cited In (12)

• Non-asymptotic error bounds for constant stepsize stochastic approximation for tracking mobile agents
• Consistency of stochastic approximation algorithm with quasi-associated random errors
• Confidence intervals from stochastic approximation
• Title not available (Why is that?)
• A stopping rule for the Robbins-Monro method
• Asymptotic confidence regions of stochastic approximation procedures in Hilbert spaces
• Title not available (Why is that?)
• A stopping rule for stochastic approximation
• A stopped stochastic approximation algorithm
• Contemporaneous statistics for estimation in stochastic actor-oriented co-evolution models
• Some results about averaging in stochastic approximation
• Designs in nonlinear regression by stochastic minimization of functionals of the mean square error matrix

This page was built for publication: Non-asymptotic confidence bounds for stochastic approximation algorithms with constant step size

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q753365)