Recursive Robust Minimax Estimation

  • É. Walter
  • H. Piet-Lahanier


An important problem arising when one wants to estimate the parameters of a model in a bounded-error context is the specification of reliable bounds for this error. In early phases of development, when no prior information is available, one may wish to know the minimum upper bound for the amplitude of the error such that the feasible parameter set is not empty. This corresponds to using a minimax estimator. For models linear in their parameters, we describe a method that takes advantage of a reparametrization in order to recursively obtain the minimax estimates and associated bounds for the error. It also provides the set of parameters compatible with any upper bound of the error. This procedure is extended to output-error models, which are nonlinear in their parameters. Its robustness to outliers is discussed and a technique is described to detect and discard them.


Polyhedral Cone Exact Description Supporting Hyperplane Autoregressive Parameter Minimax Estimation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    E. Walter and H. Piet-Lahanier, Math. Comput. Simul. 32, 449 (1990).MathSciNetCrossRefGoogle Scholar
  2. 2.
    E. Fogel and Y. F. Huang, Automatica 18, 229 (1982).MathSciNetzbMATHCrossRefGoogle Scholar
  3. 3.
    L. Pronzato, E. Walter, and H. Piet-Lahanier, in: Proceedings of the 28th IEEE Conference on Decision and Control, Tampa, FL, pp. 1952-1955 (1989).Google Scholar
  4. 4.
    G. Belforte, B. Bona, and V. Cerone, Automatica 26, 887 (1990).zbMATHCrossRefGoogle Scholar
  5. 5.
    M. Milanese and G. Belforte, IEEE Trans. Autom. Control AC-27, 408 (1982).MathSciNetCrossRefGoogle Scholar
  6. 6.
    V. Broman and M. J. Shensa, in: Proceedings of the 25th IEEE Conference on Decision and Control, Athens, Greece, pp. 1749-1752 (1986).Google Scholar
  7. 7.
    S. H. Mo and J. P. Norton, Math. Comput. Simul. 32, 481 (1990).MathSciNetCrossRefGoogle Scholar
  8. 8.
    E. Walter and H. Piet-Lahanier, IEEE Trans. Autom. Control AC-34, 911 (1989).MathSciNetCrossRefGoogle Scholar
  9. 9.
    G. Belforte and M. Milanese, in: Proceedings of the 1st IASTED International Symposium on Modeling Identification and Control, Davos, Switzerland, pp. 75-79 (1981).Google Scholar
  10. 10.
    J. P. Norton, Int. J. Control 45, 375 (1987).zbMATHCrossRefGoogle Scholar
  11. 11.
    T. Clement and S. Gentil, Math Comput. Simul. 30, 257 (1988).MathSciNetzbMATHCrossRefGoogle Scholar
  12. 12.
    M. Milanese and A. Vicino, in: System Modelling and Simulation (S. Tzafestas et al. eds.) Elsevier, Amsterdam, The Netherlands, pp. 91–96 (1989).Google Scholar
  13. 13.
    K. Keesman, Math. Comput. Simul. 32, 535 (1990).MathSciNetCrossRefGoogle Scholar
  14. 14.
    H. Piet-Lahanier and E. Walter, Math. Comput. Simul. 32, 553 (1990).MathSciNetCrossRefGoogle Scholar
  15. 15.
    P. S. Laplace, in: Mémoires de l’Académie des Sciences de Paris, pp. 1–87 (1793); Oeuvres, Vol. 11, (Reprint) Gauthier-Villars, Paris, pp. 447-558 (1895).Google Scholar
  16. 16.
    J. B. Fourier, in: Histoire de l’Académie pour 1824, pp. 325–328 (1824); Oeuvres (Reprint) Gauthier-Villars, Paris (1890).Google Scholar
  17. 17.
    A. L. Cauchy, Journal de l’École Polytechnique 13, 175 (1831); Oeuvres (Reprint) Series 2, Vol. 1, Gauthier-Villars, Paris (1905).Google Scholar
  18. 18.
    R. W. Farebrother, in: Statistical Data Analysis Based on the L 1-Norm (Y. Dodge, ed.) Elsevier, Amsterdam, The Netherlands, pp. 37–63 (1987).Google Scholar
  19. 19.
    A. Ralston, A First Course in Numerical Analysis, McGraw-Hill, New York (1965).zbMATHGoogle Scholar
  20. 20.
    E. Walter and H. Piet-Lahanier, in: Prep. 9th IFAC/IFORS Symposium on Identification and System Parameter Estimation, Budapest, Hungary. pp. 763-768 (1991).Google Scholar
  21. 21.
    M. L. Overton, in: Nonlinear Optimization 1981 (M. J. D. Powell, ed.) Academic Press, New York (1982).Google Scholar
  22. 22.
    A. van den Bos, in: Prep. 7th IFAC/IFORS Symposium on Identification and System Parameter Estimation, pp. 173-177 (1985).Google Scholar
  23. 23.
    G. Dantzig, Linear Programming and Extensions, Princeton University Press, Princeton, NJ (1963).zbMATHGoogle Scholar
  24. 24.
    N. Karmarkar, Combinatorica 4, 373 (1984).MathSciNetzbMATHCrossRefGoogle Scholar
  25. 25.
    G. Dantzig and P. Wolfe, Econometrica 29, 767 (1961).MathSciNetzbMATHCrossRefGoogle Scholar
  26. 26.
    G. Goffin and J. P. Vial, J. of Optim. Theory and Applic. 65, 409 (1990).MathSciNetzbMATHCrossRefGoogle Scholar
  27. 27.
    T. S. Motzkin, H. Raiffa, G. L. Thompson, and R. M. Thrall, in: Contributions to the Theory of Games, Vol. 2, Annals of Mathematics Study 28, (H. W. Kuhn and A. W. Tucker, eds.) Princeton University Press, Princeton, NJ, pp. 51–73 (1953).Google Scholar
  28. 28.
    B. D. O. Anderson, Automatica 21, 709 (1985).zbMATHCrossRefGoogle Scholar
  29. 29.
    M. Basseville, Automatica 24, 309 (1988).MathSciNetzbMATHCrossRefGoogle Scholar
  30. 30.
    A. Willsky, IEEE Trans. Autom. Control AC-21, 108 (1976).MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 1996

Authors and Affiliations

  • É. Walter
    • 1
  • H. Piet-Lahanier
    • 2
  1. 1.Laboratoire des Signaux et SystèmesCNRS École Supérieure d’ÉlectricitéGif-sur-Yvette CedexFrance
  2. 2.Direction des Études de SynthèseSM Office National d’Études et de Recherches AérospatialesChâtillon CedexFrance

Personalised recommendations