Convergence analysis for feedback- and weighting-based Jacobian estimates in the adaptive simultaneous perturbation algorithm

Proceedings of the IEEE Conference on Decision and Control

Volumn , Issue , 2006, Pages 5669-5674

  Spall, James C ^a  

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

Author keywords

Adaptive estimation; Jacobian matrix; Root finding; Simultaneous perturbation stochastic approximation (SPSA); Stochastic approximation; Stochastic optimization

Indexed keywords

ADAPTIVE SYSTEMS; APPROXIMATION ALGORITHMS; CONVERGENCE OF NUMERICAL METHODS; JACOBIAN MATRICES; OPTIMIZATION; PERTURBATION TECHNIQUES; RANDOM PROCESSES;

ADAPTIVE ESTIMATION; SIMULTANEOUS PERTURBATION STOCHASTIC APPROXIMATION (SPSA); STOCHASTIC APPROXIMATION; STOCHASTIC OPTIMIZATION;

FEEDBACK CONTROL;

EID: 38349120656     PISSN: 07431546     EISSN: 25762370     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (15)

1. Bhatnagar, S. (2005), "Adaptive Multivariate Three-Timescale Stochastic Approximation Algorithms for Simulation-Based Optimization," ACM Transactions on Modeling and Computer Simulation, Vol. 15, pp. 74-107.
2. Chow, Y. S. and Teicher, H. (1988), Probability Theory: Independence, Interchangeability, and Martingales (2nd ed.), Springer-Verlag, New York.
3. Fabian, V. (1971), "Stochastic Approximation," in Optimizing Methods in Statistics (J. S. Rustigi, ed.), Academic Press, New York, pp. 439-470.
4. Gerencsér, L. and Vago, Z. (2001), "The: Mathematics, of Noise-Free SPSA," Proceedings of the IEEE Conference on Decision and Control, 4-7 December 2001, Orlando, FL, pp. 4400-4405.
5. Kushner, H. J. and Yin, G. G. (2003), Stochastic Approximation and Recursive Algorithms and Applications (2nd ed.), Springer-Verlag, New York.
6. Macchi, O. and Eweda, E. (1983), "Second-Order Convergence Analysis of Stochastic Adaptive Linear Filtering," IEEE Transactions on Automatic Control, vol. AC-28, pp. 76-85.
7. Maryak, J. L. and Chin, D. C. (2001), "Global Random Optimization by Simultaneous Perturbation Stochastic Approximation," Proceedings of the American Control Conference, 25-27 June 2001, Arlington, VA, pp. 756-762.
8. Polyak, B. T. and Juditsky, A B. (1992), "Acceleration of Stochastic Approximation by Averaging," SIAM Journal on Control and Optimization, vol. 30, pp. 838-855.
9. Ruppert, D. (1985), "A Newton-Raphson Version of the Multivariate Robbins-Monro Procedure,".Annals of Statistics, vol. 13, pp. 236-245.
10. Spall, J. C. (1992), "Multivariate Stochastic Approximation Using a Simultaneous Perturbation, Gradient Approximation," IEEE Transactions on Automatic Control, vol. 37, pp. 332-341.
11. Spall, J. C. (2000), "Adaptive Stochastic Approximation by the Simultaneous Perturbation Method," IEEE Transactions on Automatic Control, vol. 45, pp. 1839-1853.
12. Spall, J. C. (2003), Introduction to Stochastic Search and Optimization: Estimation, Simulation, and Control, Wiley, Hoboken, NJ.
13. Spall, J. C. (2006), "Feedback and Weighting Mechanisms for Improving Jacobian (Hessian) Estimates in the Adaptive Simultaneous Perturbation Algorithm," Proceedings of the American Control Conference, Minneapolis, MN, 14-16 June 2006, pp., 3086-3091.
14. Yin, G. and Zhu, Y. (1992), "Averaging Procedures in Adaptive Filtering: An Efficient Approach," IEEE Transactions on Automatic Control, vol. 37, pp. 466-475.
15. Wei, C. Z. (1987), "Multivariate Adaptive Stochastic Approximation," Annals of Statistics, vol 15, pp. 1115-1130.