Adaptive stochastic approximation by the simultaneous perturbation method

IEEE Transactions on Automatic Control

Volumn 45, Issue 10, 2000, Pages 1839-1853

  Spall, James C ^a,b  

^a IEEE   (United States)

^b JOHNS HOPKINS UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ADAPTIVE ESTIMATION; ROOT FINDING; SIMULTANEOUS PERTURBATION STOCHASTIC APPROXIMATION;

ADAPTIVE CONTROL SYSTEMS; ALGORITHMS; APPROXIMATION THEORY; ASYMPTOTIC STABILITY; CONVERGENCE OF NUMERICAL METHODS; MATHEMATICAL MODELS; OPTIMIZATION; PARAMETER ESTIMATION; PERTURBATION TECHNIQUES; RANDOM PROCESSES; SYSTEM STABILITY;

CONTROL SYSTEM ANALYSIS;

EID: 0034290982     PISSN: 00189286     EISSN: None     Source Type: Journal    
DOI: 10.1109/TAC.2000.880982     Document Type: Article

References (45)

1. A. Benveniste, M. Metivier, and P. Priouret, Adaptive Algorithms and Stochastic Approximations. New York: Springer-Verlag, 1990.
2. J. R. Blum, "Approximation methods which converge with probability one," Ann. Mat. Statist., vol. 25, pp. 382-386, 1954.
3. R.W. Brennan and P. Rogers, "Stochastic optimization applied to a manufacturing system operation problem," in Proc. Winter Simulation Conf., C. Alexopoulos, K. Kang, W. R. Lilegdon, and D. Goldsman, Eds., 1995, pp. 857-864.
4. H. F. Chen, T. E. Duncan, and B. Pasik-Duncan, "A stochastic approximation algorithm with random differences," in Proc. 13th IFAC World Congr., vol. H, 1996, pp. 493-496.
5. D. C. Chin, "A more efficient global optimization algorithm based on Styblinski and Tang," Neural Networks, vol. 7, pp. 573-574, 1994.
6. _, "Comparative study of stochastic algorithms for system optimization based on gradient approximation," IEEE Trans. Syst., Man, Cybern. B, vol. 27, pp. 244-249, 1997.
7. J. Dippon and J. Renz, "Weighted means in stochastic approximation of minima," SIAM J. Contr. Optimiz., vol. 35, pp. 1811-1827, 1997.
8. S. N. Evans and N. C. Weber, "On the almost sure convergence of a general stochastic approximation procedure," Bull. Australian Math. Soc., vol. 34, pp. 335-342, 1986.
9. V. Fabian, "On asymptotic normality in stochastic approximation," Ann. Math. Stat., vol. 39, pp. 1327-1332, 1968.
10. _, "Stochastic approximation," in Optimizing Methods in Statistics, J. J. Rustagi, Ed. New York: Academic, 1971, pp. 439-470.
11. _, "On asymptotically efficient recursive estimation," Ann. Stat., vol. 6, pp. 854-866, 1978.
12. L. Gerencsér, "Rate of convergence of moments for a simultaneous perturbation stochastic approximation method for optimization," IEEE Trans. Automat. Contr., vol. 44, pp. 894-905, 1999.
13. C. Kao, W. T. Song, and S.-P Chen, "A modified quasi-Newton method for optimization in simulation," Int. J. Oper. Res, vol. 4, pp. 223-233, 1997.
14. H. J. Kushner and D. S. Clark, Stochastic Approximation for Constrained and Unconstrained Systems. New York: Springer-Verlag, 1978.
15. H. J. Kushner and G. G. Yin, Stochastic Approximation Algorithms and Applications. New York: Springer-Verlag, 1997.
16. R. G. Laha and V. K. Rohatgi, Probability Theory. New York: Wiley, 1979.
17. L. Ljung, "Applications to adaptation algorithms," in Stochastic Approximation and Optimization of Random Systems, L. Ljung, G. Pflug, and H. Walk, Eds. Basel: Birkhauser, 1992, pp. 95-113.
18. R. R. Luman, "Upgrading complex systems of systems: A CAIV methodology for warfare area requirements allocation," Mil. Oper. Res., vol. 5, no. 2, pp. 73-75, 2000.
19. O. Macchi and E. Eweda, "Second order convergence analysis of stochastic adaptive linear filtering," IEEE Trans. Automat. Contr., vol. AC-28, pp. 76-85, 1983.
20. Y. Maeda and R. J. P. De Figueiredo, "Learning rules for neuro-controller via simultaneous perturbation," IEEE Trans. Neural Networks, vol. 8, pp. 1119-1130, 1997.
21. J. L. Maryak, "Some guidelines for using iterate averaging in stochastic approximation," in Proc. IEEE Conf. Decision Contr., 1997, pp. 2287-2290.
22. M. Metivier and P. Priouret, "Applications of a Kushner and Clark lemma to general classes of stochastic algorithms," IEEE Trans. Inform. Theory, vol. IT-30, pp. 140-151, 1984.
23. M. B. Nevel'son and R. Z. Has'minskii, Stochastic Approximation and Recursive Estimation. Providence, RI: Amer. Math. Soc., 1976.
24. G. Pflug, "Applicational aspects of stochastic approximation," in Stochastic Approximation and Optimization of Random Systems, L. Ljung, G. Pflug, and H. Walk, Eds. Basel: Birkhauser, 1992, pp. 53-93.
25. B. T. Polyak and A. B. Juditsky, "Acceleration of stochastic approximation by averaging," SIAM J. Contr. Optimiz., vol. 30, pp. 838-855, 1992.
26. B. T. Polyak and Ya. Z. Tsypkin, "Optimal and robust methods for stochastic optimization," Nova J. Math., Game Theory, Algebra, vol. 6, pp. 163-176, 1997.
27. D. Ruppert, "A Newton-Raphson version of the multivariate robbins-Monro procedure," Ann. Stat., vol. 13, pp. 236-245, 1985.
28. _, "Stochastic approximation," in Handbook of Sequential Analysis, B. K. Ghosh and P. K. Sen, Eds. New York: Marcel Dekker, 1991, pp. 503-529.
29. P. Sadegh, "Constrained optimization via stochastic approximation with a simultaneous perturbation gradient approximation," Automatica, vol. 33, pp. 889-892, 1997.
30. P. Sadegh and J. C. Spall, "Optimal random perturbations for multivariate stochastic approximation using a simultaneous perturbation gradient approximation," IEEE Trans. Automat. Contr., vol. 43, pp. 1430-1434, 1998. (corrections to references, vol. 44, p. 231, 1999).
31. H.-P Schwefel, Evolution and Optimum Seeking. New York: Wiley, 1995.
32. J. C. Spall, "A stochastic approximation algorithm for large-dimensional systems in the Kiefer-Wolfowitz setting," in Proc. IEEE Conf. Decision Contr., 1988, pp. 1544-1548.
33. _, "Multivariate stochastic approximation using a simultaneous perturbation gradient approximation," IEEE Trans. Automat. Contr., vol. 37, pp. 322-341, 1992.
34. _, "A one-measurement form of simultaneous perturbation stochastic approximation," Automatica, vol. 33, pp. 109-112, 1997.
35. _, "Accelerated second-order stochastic optimization using only function measurements," in Proc. IEEE Conf. Decision Contr., 1997, pp. 1417-1424.
36. _, "Implementation of the simultaneous perturbation algorithm for stochastic optimization," IEEE Trans. Aerosp. Electron. Syst., vol. 34, pp. 817-823, 1998.
37. _, "Adaptive stochastic approximation by the simultaneous perturbation method," in Proc. IEEE Conf. Decision Contr., 1998, pp. 3872-3879.
38. J. C. Spall and J. A. Cristion, "Model-free control of nonlinear stochastic systems with discrete-time measurements," IEEE Trans. Automat. Contr., vol. 43, pp. 1198-1210, 1998.
39. M. A. Styblinski and T. S. Tang, "Experiments in nonconvex optimization: stochastic approximation with function smoothing and simulated annealing," Neural Networks, vol. 3, pp. 467-483, 1990.
40. A. Vande Wouwer, C. Renotte, M. Renotte, and M. Remy, "On the use of simultaneous perturbation stochastic approximation for neural network training," in Proc. Amer. Contr. Conf., 1999, pp. 388-392.
41. J. H. Venter, "An extension of the Robbins-Monro algorithm," Ann. Math. Stat., vol. 38, pp. 181-190, 1967.
42. H. Walk, "Foundations of stochastic approximation," in Stochastic Approximation and Optimization of Random Systems, L. Ljung, G. Pflug, and H. Walk, Eds. Basel: Birkhauser, 1991, vol. 37, pp. 2-51.
43. C. Z. Wei, "Multivariate adaptive stochastic approximation," Ann. Stat., vol. 15, pp. 1115-1130, 1987.
44. S. Yakowitz, P. L' Ecuyer, and F. Vazquez-Abad, "Global stochastic optimization with low-dispersion point sets," Oper. Res., 2000, to be published.
45. G. G. Yin and Y. Zhu, "Averaging procedures in adaptive filtering: an efficient approach," IEEE Trans. Automat. Contr., vol. 37, pp. 466-475, 1992.