Stochastic approximation algorithms: Overview and recent trends |
| |
Authors: | B Bharath V S Borkar |
| |
Affiliation: | (1) Department of Electrical Communication Engineering, Indian Institute of Science, 560 012 Bangalore, India;(2) Department of Computer Science and Automation, Indian Institute of Science, 560 012 Bangalore, India;(3) Present address: Tata Institute of Fundamental Research, Homi Bhabha Road, 400 005 Mumbai, India |
| |
Abstract: | Stochastic approximation is a common paradigm for many stochastic recursions arising both as algorithms and as models of some
stochastic dynamic phenomena. This article gives an overview of the known results about their asymptotic behaviour, highlights
recent developments such as distributed and multiscale algorithms, and describes existing and potential applications, and
other related issues.
The work of the second author is supported by the DST grant III 5(12)/96-ET. |
| |
Keywords: | Stochastic approximation asymptotic convergence stochastic optimization learning algorithms |
本文献已被 SpringerLink 等数据库收录! |
|