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
[1]  
Abdelhamid S(1973)Transformations of observations in stochastic approximation Ann. Stat. 1 1158-1174
[2]  
Anbar D(1973)On optimal estimation methods using stochastic approximation procedures Ann. Stat. 1 1175-1184
[3]  
Arthur B(1983)A generalized urn problem and its applications Cybernetics 19 61-71
[4]  
Ermoliev Y(1983)Neuron-like elements that can solve difficult learning control problems IEEE Trans. Syst., Man Cybern. 13 835-846
[5]  
Kaniovski Y(1997)Weak convergence of recursions Stoch. Processes Appl. 68 65-82
[6]  
Barto A(1999)A dynamical system approach to stochastic optimization SIAM J. Control Optim. 34 437-472
[7]  
Sutton R(1998)Recursive algorithms, urn processes and chaining number of chain recurrent sets Ergodic Theory Dyn. Syst. 18 53-87
[8]  
Anderson C(1997)Multiscale stochastic approximation for parametric optimization of hidden Markov models Probab. Eng. Inf. Sci. 11 509-522
[9]  
Basak G(1998)A two time-scale stochastic approximation scheme for simulation-based parametric optimization Probab. Eng. Inf. Sci. 12 519-531
[10]  
Hu I(1998)Robust parameter optimization of hidden Markov models J. Indian Inst. Sci. 78 119-130
12345678910