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

DOI10.1007/BF01301683zbMath0716.62081OpenAlexW2003163868WikidataQ59255200 ScholiaQ59255200MaRDI QIDQ753365

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

zbMATH Keywords

stopping timecoverage probabilitycomparison resultconfidence regionsconstant 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)

Related Items (5)

Some results about averaging in stochastic approximation ⋮ Contemporaneous statistics for estimation in stochastic actor-oriented co-evolution models ⋮ A stopping rule for stochastic approximation ⋮ Non-asymptotic error bounds for constant stepsize stochastic approximation for tracking mobile agents ⋮ Designs in nonlinear regression by stochastic minimization of functionals of the mean square error matrix

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A Newton-Raphson version of the multivariate Robbins-Monro procedure
• Stochastic approximation methods for constrained and unconstrained systems
• Stochastic Minimization with Constant Step-Size: Asymptotic Laws
• COMPARISON OF SOME NON-LINEAR AUTOREGRESSIVE PROCESSES
• Asymptotic Properties of Stochastic Approximations with Constant Coefficients
• A measure of the tracking capability of recursive stochastic algorithms with constant gains
• On a new stopping rule for stochastic approximation
• Bounded Length Confidence Intervals for the Zero of a Regression Function
• A limit theorem for the Robbins-Monro approximation
• Some Multivariate Chebyshev Inequalities with Extensions to Continuous Parameter Processes
• A Stochastic Approximation Method

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