Sufficient and necessary condition for the convergence of stochastic approximation algorithms

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.

MoreLess

Year of publication:	2006
Authors:	Chen, Neiping ; Liu, Wenbin ; Feng, Jianfeng
Published in:	Statistics & Probability Letters. - Elsevier, ISSN 0167-7152. - Vol. 76.2006, 2, p. 203-210
Publisher:	Elsevier
Keywords:	Stochastic approximation algorithms Simulated annealing Local minima Global minima

More details

Type of publication:	Article
Source:	RePEc - Research Papers in Economics

Persistent link: https://www.econbiz.de/10005254948