A strong approximation theorem for stochastic recursive algorithms

作     者：Borkar, VS Mitter, SK 

作者机构：Indian Inst Sci Dept Comp Sci & Automat Bangalore 560012 Karnataka India MIT Informat & Decis Syst Lab Cambridge MA 02139 USA 

出 版 物：《JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS》 (优选法理论与应用杂志)

年 卷 期：1999年第100卷第3期

页      面：499-513页

核心收录：

学科分类：1201[管理学-管理科学与工程(可授管理学、工学学位)] 07[理学] 070104[理学-应用数学] 0701[理学-数学] 

基　　金：Center for Intelligent Control Systems U.S. Army, (DAAL03-92-G-0115) Massachusetts Institute of Technology, MIT 

主　　题：stochastic algorithms approximation of stochastic differential equations constant stepsize algorithms asymptotic behavior 

摘      要：The constant stepsize analog of Gelfand-Mitter type discrete-time stochastic recursive algorithms is shown to track an associated stochastic differential equation in the strong sense, i.e., with respect to an appropriate divergence measure.