Asymptotic properties of two time-scale stochastic approximation algorithms with constant step sizes

被引：0
|
作者：
Tadic, VB [1 ]
Meyn, SP [1 ]
机构：
[1] Univ Melbourne, Dept Elect & Elect Engn, Parkville, Vic 3010, Australia
来源：
PROCEEDINGS OF THE 2003 AMERICAN CONTROL CONFERENCE, VOLS 1-6 | 2003年
关键词：
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Asymptotic properties of two time-scale stochastic approximation algorithms with constant step sizes are analyzed in this paper. The analysis is carried out for the algorithms with additive noise, as well as for the algorithms with non-additive noise. The algorithms with additive noise are considered for the case where the noise is state-dependent and admits the decomposition as a sum of a martingale difference sequence and a telescoping sequence. The algorithms with non-additive noise are analyzed for the case where the noise satisfies uniform or strong mixing conditions, as well as for the case where the noise is a Markov chain controlled by the algorithm states.
引用
收藏
页码：4426 / 4431
页数：6
相关论文
共 50 条
  • [31] TREATMENT OF ASYMPTOTIC ACOUSTIC-SIGNALS BY TIME-SCALE REPRESENTATION
    KRONLAND, R
    GROSSMANN, A
    ESCUDIE, B
    JOURNAL DE PHYSIQUE IV, 1992, 2 (C1): : 1117 - 1120
  • [32] Convergence rate of linear two-time-scale stochastic approximation
    Konda, VR
    Tsitsiklis, JN
    ANNALS OF APPLIED PROBABILITY, 2004, 14 (02): : 796 - 819
  • [33] Asymptotic properties of quasi-optimal stochastic approximation algorithms under unknown noise density
    Nazin, A.V.
    Avtomatika i Telemekhanika, 1995, (10): : 70 - 77
  • [34] Asymptotic properties of quasi-optimal algorithms of stochastic approximation under unknown density of noise
    Nazin, AV
    AUTOMATION AND REMOTE CONTROL, 1995, 56 (10) : 1412 - 1418
  • [35] Stochastic Learning Under Random Reshuffling With Constant Step-Sizes
    Ying, Bicheng
    Yuan, Kun
    Vlaski, Stefan
    Sayed, Ali H.
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2019, 67 (02) : 474 - 489
  • [36] Parallel Implementation of Simultaneous Perturbation Stochastic Approximation with Adaptive Step Sizes
    Fan, Yue
    Liu, Tiegang
    PROCEEDINGS OF THE 2018 2ND INTERNATIONAL CONFERENCE ON ALGORITHMS, COMPUTING AND SYSTEMS (ICACS 2018), 2018, : 3 - 6
  • [37] Passive stochastic approximation with constant step size and window width
    Yin, GG
    Yin, KW
    IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1996, 41 (01) : 90 - 106
  • [38] ε-Dependent Controllability for Two Time-Scale Systems
    胡叶楠
    孙富春
    刘华平
    吴昊
    Tsinghua Science and Technology, 2009, (02) : 271 - 280
  • [39] Linear Two-Time-Scale Stochastic Approximation A Finite-Time Analysis
    Doan, Thinh T.
    Romberg, Justin
    2019 57TH ANNUAL ALLERTON CONFERENCE ON COMMUNICATION, CONTROL, AND COMPUTING (ALLERTON), 2019, : 399 - 406
  • [40] Joint time-scale and TDOA estimation: Analysis and fast approximation
    Chan, YT
    Ho, KC
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2005, 53 (08) : 2625 - 2634
12345