Necessary and Sufficient Conditions for Convergence of Stochastic Approximation Algorithms

Liu, Steve Wenbin and Chen, Neiping and Feng, Jianfeng (2006) Necessary and Sufficient Conditions for Convergence of Stochastic Approximation Algorithms. Probability and Statistics Letter, 76 (2). pp. 203-210. ISSN 0167-7152 . (The full text of this publication is not available from this repository)

The full text of this publication is not available from this repository. (Contact us about this Publication)

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
Uncontrolled keywords: stochastic approximation algorithms; simulated annealing; local minima; global minima
Subjects: H Social Sciences > HA Statistics > HA33 Management Science
Divisions: Faculties > Social Sciences > Kent Business School
Depositing User: Steve Wenbin Liu
Date Deposited: 07 Sep 2008 15:21
Last Modified: 23 Jun 2014 11:03
Resource URI: http://kar.kent.ac.uk/id/eprint/8487 (The current URI for this page, for reference purposes)
  • Depositors only (login required):