Strong consistency of a class of recursive stochastic gradient algorithms

Hersh, M.A. and Zarrop, M.B. (1986) Strong consistency of a class of recursive stochastic gradient algorithms. International Journal of Control, 43(4), pp. 1115-1123. (doi: 10.1080/00207178608933527)

Full text not currently available from Enlighten.

Abstract

In this work, strong consistency results for a class of stochastic gradient algorithms are developed where the system is not necessarily minimum-phase or stable and is assumed to be of the CARMA form. The analysis uses only standard martingale results, and strong consistency is shown to hold under certain persistent excitation conditions.

Item Type:Articles
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Hersh, Dr Marion
Authors: Hersh, M.A., and Zarrop, M.B.
College/School:College of Science and Engineering > School of Engineering > Biomedical Engineering
Journal Name:International Journal of Control
Publisher:Taylor and Francis
ISSN:0020-7179
ISSN (Online):1366-5820

University Staff: Request a correction | Enlighten Editors: Update this record