欢迎访问中国科学院大学学报,今天是
数学与物理学

基于平均化的截尾随机逼近算法

  • 刘仁龙 ,
  • 杨建奎 ,
  • 熊世峰
展开
  • 1. 北京邮电大学理学院, 北京 100876;
    2. 中国科学院数学与系统科学研究院, 北京 100190

收稿日期: 2014-04-16

  修回日期: 2014-08-06

  网络出版日期: 2015-05-15

基金资助

国家自然科学基金(11271355,11101050,11471172)资助

Averaging-based truncated stochastic approximation algorithm

  • LIU Renlong ,
  • YANG Jiankui ,
  • XIONG Shifeng
Expand
  • 1. School of Science, Beijing University of Posts and Telecommunications, Beijng 100876, China;
    2. Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100190, China

Received date: 2014-04-16

  Revised date: 2014-08-06

  Online published: 2015-05-15

摘要

考察带有随机干扰线性系统的随机逼近问题. 基于Polyak和Juditsky(SIAM J. Control & Optimization, 1992, 30:838-855)中的平均化加速算法,提出平均化的截尾算法. 证明该算法下随机逼近序列的强相合性和渐近正态性.

本文引用格式

刘仁龙 , 杨建奎 , 熊世峰 . 基于平均化的截尾随机逼近算法[J]. 中国科学院大学学报, 2015 , 32(3) : 289 -294 . DOI: 10.7523/j.issn.2095-6134.2015.03.001

Abstract

In this work the stochastic approximation problem of perturbed linear systems was examined. Inspired by the averaging-based accelerated algorithm of Polyak and Juditsky(SIAM J. Control & Optimization,1992,30:838-855), we propose an averaging-based truncated algorithm. The almost sure convergence and asymptotic normality of the sequence defined by this algorithm are proved.

参考文献

[1] Robbins H, Siegmund D. A stochastic approximation method[J]. Ann Math Statist, 1951,22:400-407.

[2] Kiefer E, Wolfovitz J. Stochastic estimation of the maximum of a regression function[J]. Ann Math Statist, 1952,23:462-466.

[3] Kornfelev A P, Stochastic recurrent procedures[M]. Nauka, 1981 (in Russian).

[4] Kushner H J, Clark D S, Stochastic approximation methods for constrained and unconstrained systems[M].Springer, New York, 1978.

[5] Nemirovski A, Juditsky A, Lan G,et al. Robust stochastic approximation approach to stochastic programming[J]. SIAM J Optim, 2009,19:1 574-1 609.

[6] Stein M L, Chen J, Anitescu M. Stochastic approximation of score functions for Gaussian processes[J]. Ann Appl Stat, 2013,7:1 162-1 191.

[7] Benaim M, Faure M. Stochastic approximation, cooperative dynamics and supermodular games[J]. Ann Appl Probab, 2012,22:2 133-2 164.

[8] Koshal J, Nedic A, Shanbhag U V. Regularized iterative stochastic approximation methods for stochastic variational inequality problems[J]. IEEE Trans Automat Control, 2013, 58:594-609.

[9] Polyak B T. New stochastic approximation type procedures[J]. Avtomat Telemekh, 1990,N7:98-107(in Russian).

[10] Ruppert D. Efficient estimators from a slowly convergent Robbins-Monro process[R]. Tech Report No. 781, School of Operations Research and Industrial Engineering, Cornell University, Ithaca, NY, 1988.

[11] Polyak B T, Juditsky A B. Acceleration of stochastic approximation by averaging[J]. SIAM J Control and optimization, 1992,30:838-855.

[12] 陈翰馥, 朱允民.随机逼近[M]. 上海:上海科学技术出版社, 1996.

[13] 陈翰馥, 扩展截尾的随机逼近算法[J].系统科学与数学, 2012, 12:1 472-1 487

[14] Liptzer R S, Shiryaev A N. Martingale theory[M]. Nauka, Moscow,1986(in Russian).

文章导航

/