ENGLISH

Stochastic Approximation and Its Application

Book information

Publisher
Springer
Year
2002
ISBN
9780306481666, 9781402008061, 1402008066
LCC
QA274.2 .C538 2002
Open Library ID
OL21801438M
Language
english
Format
PDF
Filesize
6 MB (6645943 bytes)
Series
Nonconvex Optimization and Its Applications
Edition
1
Pages
369\369
Library
kolxoz
Time added
2009-07-20 03:45:11

Description

This book presents the recent development of stochastic approximation algorithms with expanding truncations based on the TS (trajectory-subsequence) method, a newly developed method for convergence analysis. This approach is so powerful that conditions used for guaranteeing convergence have been considerably weakened in comparison with those applied in the classical probability and ODE methods. The general convergence theorem is presented for sample paths and is proved in a purely deterministic way. The sample-path description of theorems is particularly convenient for applications. Convergence theory takes both observation noise and structural error of the regression function into consideration. Convergence rates, asymptotic normality and other asymptotic properties are presented as well. Applications of the developed theory to global optimization, blind channel identification, adaptive filtering, system parameter identification, adaptive stabilization and other problems arising from engineering fields are demonstrated. Audience: Researchers and students of both graduate and undergraduate levels in systems and control, optimization, signal processing, communication and statistics.

Similar books