Strong points of weak convergence: A study using RPA gradient estimation for automatic learning

DOI10.1016/S0005-1098(99)00034-5zbMATH Open0940.93078OpenAlexW2142929170WikidataQ128067155 ScholiaQ128067155MaRDI QIDQ1301439FDOQ1301439

Authors: Felisa J. Vázquez-Abad 

Publication date: 2 November 1999

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/s0005-1098(99)00034-5

Recommendations

• Convergence of parameter sensitivity estimates in a stochastic experiment
• A Globally Convergent Stochastic Approximation
• Gradient procedures for stochastic approximation with dependent noise and their asymptotic behaviour
• On a Finite Deformation of a Cone
• Convergence of stochastic approximation coupled with perturbation analysis in a class of manufacturing flow control models

zbMATH Keywords

learningstochastic approximationweak convergenceestimate of the gradient vectornon-reset version of the estimatorregenerate estimation approach

Mathematics Subject Classification ID

Stochastic approximation (62L20) Stochastic programming (90C15) Programming in abstract spaces (90C48) Stochastic learning and adaptive control (93E35)

Cited In (2)

• A perturbation analysis approach to phantom estimators for waiting times in the \(G/G/1\) queue
• Perturbation analysis of inhomogeneous finite Markov chains

This page was built for publication: Strong points of weak convergence: A study using RPA gradient estimation for automatic learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1301439)