Exact bounds for the rate of convergence in general stochastic approximation procedures
作者:
Valery Koval,
Rainer Schwabe,
期刊:
Stochastic Analysis and Applications
(Taylor Available online 1998)
卷期:
Volume 16,
issue 3
页码: 501-515
ISSN:0736-2994
年代: 1998
DOI:10.1080/07362999808809545
出版商: Marcel Dekker, Inc.
数据来源: Taylor
摘要:
In this paper exact constants are given for the rate of convergence of the solutionxnof the nonlinear difference equationtowards the root θ offunder very general conditions on the steplengthsan, on the weighting factorsbnand on the random noisevn. Moreover, an almost sure representation is developed for the deviationxn– θ by weighted sums of (independent) random variables
点击下载:
PDF (449KB)
返 回