Weighted averaging and stochastic approximation

Author

Ang, I-jengw ; Chong, Edwink p. ; Kulkar, Sanjeerv

Author_Institution

Sch. of Electr. Eng. & Comput. Eng., Purdue Univ., West Lafayette, IN, USA

Volume

1

fYear

1996

fDate

11-13 Dec 1996

Firstpage

1071

Abstract

We explore the relationship between weighted averaging and stochastic approximation algorithms, and study their convergence via a sample-path analysis. We prove that the convergence of a stochastic approximation algorithm is equivalent to the convergence of the weighted average of the associated noise sequence. We also present necessary and sufficient noise conditions for convergence of the average of the output of a stochastic approximation algorithm in the linear case. We show that the averaged stochastic approximation algorithms can tolerate a larger class of noise sequences than the stand-alone stochastic approximation algorithms

Keywords

approximation theory; convergence of numerical methods; noise; sequences; convergence; necessary and sufficient noise conditions; noise sequence; sample-path analysis; stochastic approximation; weighted averaging; Aging; Algorithm design and analysis; Approximation algorithms; Convergence; Hilbert space; Parameter estimation; Stochastic processes; Stochastic resonance; Sufficient conditions; Uncertainty;

fLanguage

English

Publisher

ieee

Conference_Titel

Decision and Control, 1996., Proceedings of the 35th IEEE Conference on

Conference_Location

Kobe

ISSN

0191-2216

Print_ISBN

0-7803-3590-2

Type

conf

DOI

10.1109/CDC.1996.574643

Filename

574643