Advertisement

Stability of Random Iterative Mappings

  • László Gerencsér
Part of the International Series in Operations Research & Management Science book series (ISOR, volume 46)

Abstract

We consider a sequence of not necessarily i.i.d. random mappings that arise in discrete-time fixed-gain recursive estimation processes. This is related to the sequence generated by the discrete-time deterministic recursion defined in terms of the averaged field. The tracking error is majorated by an L-mixing process the moments of which can be estimated. Thus we get a discrete-time stochastic averaging principle. The paper is a simplification and extension of Gerencsér (1996).

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Benveniste, A., M. Métivier, and P. Priouret. (1990). Adaptive algorithms and stochastic approximations. Springer-Verlag, Berlin.CrossRefGoogle Scholar
  2. Bittanti, S. and M. Campi. (1994). Bounded error identification of time-varying parameters by RLS techniques. IEEE Trans. Automat. Contr., 39(5): 1106–1110.MathSciNetCrossRefGoogle Scholar
  3. Caines, P. E. (1988). Linear Stochastic Systems. Wiley.Google Scholar
  4. Campi, M. (1994). Performance of RLS identification algorithms with forgetting factor: a ø-mixing approach. J. of Mathematical Systems, Estimation and Control, 4:1–25.MathSciNetzbMATHGoogle Scholar
  5. Djereveckii, D. P. and A.L. Fradkov. (1974). Application of the theory of Markov-processes to the analysis of the dynamics of adaptation algorithms. Automation and Remote Control, (2):39–48.MathSciNetGoogle Scholar
  6. Djereveckii, D. P. and A.L. Fradkov. (1981). Applied theory of discrete adaptive control systems. Nauka, Moscow. In Russian.Google Scholar
  7. Geman, S. (1979). Some averaging and stability results for random differential equations. SIAM Journal of Applied Mathematics, 36:87–105.MathSciNetCrossRefGoogle Scholar
  8. Gerencsér, L. (1989). On a class of mixing processes. Stochastics, 26:165–191.MathSciNetzbMATHGoogle Scholar
  9. Gerencsér, L. (1995). Rate of convergence of the LMS algorithm. Systems and Control Letters, 24:385–388.MathSciNetCrossRefGoogle Scholar
  10. Gerencsér, L. (1996). On fixed gain recursive estimation processes. J. of Mathematical Systems, Estimation and Control, 6:355–358. Retrieval code for full electronic manuscript: 56854.MathSciNetzbMATHGoogle Scholar
  11. Gerencsér, L. and Zs. Vágó. (2001). A general framework for noise-free SPSA. In Proceedings of the 40-th Conference on Decision and Control, CDC’01, page submitted.Google Scholar
  12. Guo, L. (1990). Estimating time-varying parameters by the Kalman-filter based algorithm: stability and convergence. IEEE Trans. Automat. Contr., 35:141–157.MathSciNetCrossRefGoogle Scholar
  13. Györfi, L. and H. Walk. (1996). On the average stochastic approximation for linear regression. SIAM J. Control and Optimization, 34(1):31–61.MathSciNetCrossRefGoogle Scholar
  14. Joslin, J. A. and A. J. Heunis. (2000). Law of the iterated logarithm for a constant-gain linear stochastic gradient algorithm. SIAM J. on Control and Optimization, 39:533–570.MathSciNetCrossRefGoogle Scholar
  15. Kouritzin, M. (1994). On almost-sure bounds for the LMS algorithm. IEEE Trans. Informat. Theory, 40:372–383.CrossRefGoogle Scholar
  16. Kushner, H. J. and A. Schwartz. (1984). Weak convergence and asymptotic properties of adaptive filters with constant gains. IEEE Trans. Informat. The-ory, 30(2): 177–182.MathSciNetCrossRefGoogle Scholar
  17. Ljung, L. (1977). Analysis of recursive stochastic algorithms. IEEE Trans. Automat. Contr., 22:551–575.MathSciNetCrossRefGoogle Scholar
  18. Ljung, L. and T. Söderström. (1983). Theory andpractice of recursive identification. The MIT Press.Google Scholar
  19. Meyn, S. P. and P.E. Caines. (1987). A new approach to stochastic adaptive control. IEEE Trans. Automat. Contr., 32:220–226.MathSciNetCrossRefGoogle Scholar
  20. Sanders, J. A. and F. Verhulst. (1985). Averaging methods in nonlinear dynamical systems. Springer-Verlag, Berlin.CrossRefGoogle Scholar
  21. Spall, J. C. (1992). Multivariate stochastic approximation using a simultaneous perturbation gradient approximation. IEEE Trans. Automat. Contr., 37:332–341.MathSciNetCrossRefGoogle Scholar
  22. Spall, J. C. (1997). A one-measurement form of simultaneous perturbation stochastic approximation. Automatica, 33:109–112.MathSciNetCrossRefGoogle Scholar
  23. Spall, J. C. (2000). Adaptive stochastic approximation by the simultaneous perturbation method. IEEE Trans. Automat. Contr, 45:1839–1853.MathSciNetCrossRefGoogle Scholar
  24. Yakowitz, S. (1993). A globally convergent stochastic approximation. SIAM J. Control and Optimization, 31:30–40.MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Science + Business Media, Inc. 2002

Authors and Affiliations

  • László Gerencsér
    • 1
  1. 1.Computer and Automation InstituteHungarian Academy of SciencesBudapestHungary

Personalised recommendations