Stochastic approximation algorithms: Overview and recent trends

被引：0
作者：
B Bharath
V S Borkar
机构：
[1] Indian Institute of Science,Department of Electrical Communication Engineering
[2] Indian Institute of Science,Department of Computer Science and Automation
[3] Tata Institute of Fundamental Research,undefined
来源：
Sadhana | 1999年 / 24卷
关键词：
Stochastic approximation; asymptotic convergence; stochastic optimization; learning algorithms;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
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.
引用
收藏
页码：425 / 452
页数：27
相关论文
共 168 条
[11]  
Wey C-Z(1982)A stochastic method for global optimization Math. Program. 22 125-140
[12]  
Benaim M(1997)Learning through reinforcement and replicator dynamics J. Econ. Theory 77 1-14
[13]  
Benaim M(1999)Recursive self-tuning control of finite Markov chains Appl. Math. 24 169-188
[14]  
Bhatnagar S(1999)Distributed computation of fixed points of ∞-nonexpansive maps Indian Acad. Sci. Proc. Math. Sci. 106 289-300
[15]  
Borkar V(1999)Stochastic approximation with two time scales Syst. Control Lett. 29 291-294
[16]  
Bhatnagar S(1998)Asynchronous stochastic approximation SIAM J. Control Optim. 36 840-851
[17]  
Borkar V(1999)A strong approximation theorem for stochastic recursive algorithms J. Optim. Theor. Appl. 10 499-513
[18]  
Bharath B(1998)Some pathological traps for stochastic approximation SIAM J. Control Optim. 36 1293-1314
[19]  
Borkar V(1998)The dynamic system method and the traps Adv. Appl. Probab. 30 137-151
[20]  
Boender C(1999)Les algorithms stochastiques contournent — ils les pieges? Ann. Inst. Henri Poincare 32 395-427
12345678910