Optimal random perturbations for stochastic approximation using a simultaneous perturbation gradient approximation

IEEE Transactions on Automatic Control

Volumn 43, Issue 10, 1998, Pages 1480-1484

  Sadegh, Payman ^a   Spall, James C ^b  

^a TECHNICAL UNIVERSITY OF DENMARK   (Denmark)

^b JOHNS HOPKINS UNIVERSITY APPLIED PHYSICS LABORATORY   (United States)

Author keywords

Experiment design; Optimal probability distribution; Optimization; SPSA; Stochastic approximation

Indexed keywords

ALGORITHMS; APPROXIMATION THEORY; ERROR ANALYSIS; MAXIMUM LIKELIHOOD ESTIMATION; MONTE CARLO METHODS; OPTIMIZATION; PERTURBATION TECHNIQUES; PROBABILITY DISTRIBUTIONS; RANDOM PROCESSES; VECTORS;

OPTIMAL RANDOM PERTURBATIONS; SIMULTANEOUS PERTURBATION STOCHASTIC APPROXIMATION (SPSA) ALGORITHMS;

OPTIMAL CONTROL SYSTEMS;

EID: 0032186926     PISSN: 00189286     EISSN: None     Source Type: Journal    
DOI: 10.1109/9.720513     Document Type: Article

References (16)

1. G. Cauwenberghs, "Analog VLSI autonomous systems for learning and optimization," Ph.D. dissertation, Dept. of Electrical Engineering, California Inst. Technol., 1994.
2. D. C. Chin, "A more efficient global optimization based on Styblinski and Tang," Neural Nets, vol. 7, pp. 573-574, 1994.
3. _, "Comparative study of stochastic approximation algorithms for system optimization based on gradient approximations," IEEE Trans. Syst., Man, and Cybern., vol. 27, pp. 244-249, 1997.
4. V. Fabian, "Stochastic approximation, in Optimizing Methods in Statistics, J. J. Rustagi, Ed. New York: Academic, 1971, pp. 439-470.
5. V. V. Fedorov, Theory of Optimal Experiments. New York: Academic, 1972.
6. G. C. Goodwin and R. L. Payne, Dynamic System Identification: Experiment Design and Data Analysis. New York: Academic, 1977.
7. S. V. Gusev and T. P. Krasulina, "An algorithm for stochastic approximation with a preassigned probability of not exceeding a required threshold," J. Computer and Syst. Sciences Int., vol. 33, pp. 39-41, 1995.
8. S. D. Hill and M. C. Fu, "Transfer optimization via simulation perturbation stochastic approximation," in Proc. Winter Smulation Conf., 1995, pp. 242-249.
9. H. J. Kushner and D. S. Clark, Stochastic Approximation for Constrained and Unconstrained Systems New York: Springer-Verlag, 1978.
10. L. Ljung, System Identification: Theory for the User. Englewood Cliffs, NJ: Prentice-Hall, 1987.
11. Y. Maeda, H. Hirano, and Y. Kanata, "A learning rule of neural networks via simultaneous perturbation and its hardware implementation," Neural Nets, vol. 8, pp. 251-259, 1995.
12. T. Parisini and A. Alessandri, "Non-linear modeling and state estimation in a real power plant using neural networks and stochastic approximation," in Proc. American Control Conf., 1995, pp. 1561-1567.
13. F. Rezayat, "On the use of an SPSA-based model free controller in quality improvement," Automatica, vol. 31, pp. 913-915, 1995.
14. D. Ruppert, "Kiefer-Wolfowitz procedure," in Encyclopedia of Statistical Sciences, S. Kotz and N. L. Johnson, Eds. Wiley, 1983, pp. 379-381.
15. J. C. Spall, "A stochastic approximation technique for generating maximum likelihood parameter estimates," in Proc. American Contr. Conf., 1987, pp. 1161-1167.
16. _, "Multivariate stochastic approximation using a simultaneous perturbation gradient approximation," IEEE Trans. Automat. Contr., vol. 37, pp. 332-341, Mar. 1992.