Skip to main content
Kent Academic Repository

Sufficient and necessary condition for the convergence of stochastic approximation algorithms

Liu, Wenbin, Chen, Neiping, Feng, Jianfeng (2006) Sufficient and necessary condition for the convergence of stochastic approximation algorithms. Probability and Statistics Letter, 76 (2). pp. 203-210. ISSN 0167-7152. (doi:10.1016/j.spl.2005.07.020) (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided) (KAR id:8487)

The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided.
Official URL:
https://doi.org/10.1016/j.spl.2005.07.020

Abstract

We present a sufficient and necessary condition for the convergence of stochastic approximation algorithms, which were proposed 50 years ago, have been widely applied to various areas and intensively investigated in theory. In the literature, only various sufficient conditions are known. The obtained condition is simple and has a clear physical meaning.

Item Type: Article
DOI/Identification number: 10.1016/j.spl.2005.07.020
Uncontrolled keywords: stochastic approximation algorithms; simulated annealing; local minima; global minima
Subjects: H Social Sciences > HA Statistics > HA33 Management Science
Divisions: Divisions > Kent Business School - Division > Kent Business School (do not use)
Depositing User: Steve Liu
Date Deposited: 07 Sep 2008 15:21 UTC
Last Modified: 11 Dec 2023 12:48 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/8487 (The current URI for this page, for reference purposes)

University of Kent Author Information

  • Depositors only (login required):

Total unique views for this document in KAR since July 2020. For more details click on the image.