Formal Comparison of Simultaneous Perturbation Stochastic Approximation and Random Direction Stochastic Approximation

被引：2

作者：

Peng, Ducheng ^{[1
]}

Chen, Yiwen ^{[2
]}

Spall, James C. ^{[1
,3
]}

机构：

[1] Johns Hopkins Univ, Appl Math & Stat Dept, Whitehead Hall,3400 North Charles St, Baltimore, MD 21218 USA

[2] Johns Hopkins Univ, Appl Math & Stat Dept, Baltimore, MD USA

[3] JHU, Appl Phys Lab & Res, Baltimore, MD USA

来源：

2023 AMERICAN CONTROL CONFERENCE, ACC | 2023年

关键词：

OPTIMIZATION; ALGORITHMS; CONTROLLER; SYSTEMS;

D O I：

10.23919/ACC55779.2023.10156400

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Stochastic approximation (SA) algorithms can be used in system optimization problems when only noisy measurements of a system are available. This paper formally compares the performance of two popular SA algorithms in a multivariate Kiefer-Wolfowitz setting of simultaneous-perturbation SA (SPSA) and the random-directions SA (RDSA). This paper provides sufficient conditions to demonstrate which algorithm has the smaller asymptotic mean squared error (MSE) and numerically presents comparison of SPSA and RDSA in a test function and a model-free control system. The theory and supporting numerics indicate that SPSA has better efficiency (lower MSE) across a broad range of problem settings.

引用

页码：744 / 749

页数：6

共 50 条

[1] Global random optimization by simultaneous perturbation stochastic approximation
Maryak, JL
Chin, DC
PROCEEDINGS OF THE 2001 CONGRESS ON EVOLUTIONARY COMPUTATION, VOLS 1 AND 2, 2001, : 910 - 916
[2] Global random optimization by simultaneous perturbation stochastic approximation
Maryak, John L.
Chin, Daniel C.
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2008, 53 (03) : 780 - 783
[3] Global random optimization by simultaneous perturbation stochastic approximation
Maryak, JL
Chin, DC
PROCEEDINGS OF THE 2001 AMERICAN CONTROL CONFERENCE, VOLS 1-6, 2001, : 756 - 762
[4] Global random optimization by Simultaneous Perturbation Stochastic Approximation
Maryak, JL
Chin, DC
JOHNS HOPKINS APL TECHNICAL DIGEST, 2004, 25 (02): : 91 - 100
[5] Global random optimization by simultaneous perturbation stochastic approximation
Maryak, JL
Chin, DC
WSC'01: PROCEEDINGS OF THE 2001 WINTER SIMULATION CONFERENCE, VOLS 1 AND 2, 2001, : 307 - 312
[6] A Parallelized Combined Direction Simultaneous Perturbation Stochastic Approximation Algorithm
Zhao, Hao
Liu, Tiegang
2017 2ND IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND APPLICATIONS (ICCIA), 2017, : 141 - 144
[7] Optimal random perturbations for stochastic approximation using a simultaneous perturbation gradient approximation
Sadegh, P
Spall, JC
PROCEEDINGS OF THE 1997 AMERICAN CONTROL CONFERENCE, VOLS 1-6, 1997, : 3582 - 3586
[8] Optimal random perturbations for stochastic approximation using a simultaneous perturbation gradient approximation
Sadegh, P
Spall, JC
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 1998, 43 (10) : 1480 - 1484
[9] Optimal random perturbations for stochastic approximation using a simultaneous perturbation gradient approximation
Technical Univ of Denmark, Lyngby, Denmark
IEEE Trans Autom Control, 10 (1480-1484):
[10] Simultaneous perturbation stochastic approximation of nonsmooth functions
Bartkute, Vaida
Sakalauskas, Leonidas
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2007, 181 (03) : 1174 - 1188

← 1 2 3 4 5 →