On a proof of Robbins-Monro algorithm

DOI10.1007/BF00940033MaRDI QIDQ1117842zbMATH OpenOpenAlexFDO

Authors S. H. Smith

Publication date 1990

Published in Journal of Optimization Theory and Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/bf00940033

zbMATH Keywords

descent directiongradient evaluationsMonte Carlo simulationsRobbins-Monro algorithmsstationary pointsstochastic algorithmstochastic approximationsupermartingales

Mathematics Subject Classification ID

Numerical methods based on nonlinear programming (49M37) Numerical mathematical programming methods (65K05) Nonlinear programming (90C30)

Review text

We point out that the main result in a previous paper of the author [ibid. 61, 473-486 (1989; Zbl 0644.90079)] is not new.

Cites work

• A stochastic algorithm using one sample point per iteration and diminishing step-sizes
• Analysis of recursive stochastic algorithms
• On a proof of Robbins-Monro algorithm
• Stochastic approximation methods for constrained and unconstrained systems

Cited in

(4)

• On a proof of Robbins-Monro algorithm
• A derivation of Kohnert's algorithm from Monk's rule
• The Robbins problem: computer proofs and human proofs
• A Robbins–Monro-based Sequential Procedure

This page was built for publication: On a proof of Robbins-Monro algorithm

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1117842)