Advertisement

The averaging principle for a class of stochastic algorithms in adaptive filtering

  • Michel Metivier
Conference paper
Part of the Lecture Notes in Control and Information Sciences book series (LNCIS, volume 91)

Keywords

Slow Variation Adaptive Filter Stochastic Approximation Noisy Channel Learning Period 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Benveniste, A., Goursat, M., Ruget, G,: Analysis of stochastic approximation schemes with discontinuous dependent forcing terms. IEEE Trans. Autom. Control, Vol.AC-25, 6, 1980.Google Scholar
  2. 2.
    Bouton, C.: Approximation gaussienne d'algorithmes stochastiques. Thèse 3e Cycle, Paris (1985). Preprint CMAP, Ecole Polytechnique.Google Scholar
  3. 3.
    Eweda, E., Macchi, O.: Convergence analysis of an adaptive linear estimation algorithm. IEEE Trans. Autom. Control, Vol.AC-29, 2, 1984, 119–123.Google Scholar
  4. 4.
    Eweda, E., Macchi, O.: Convergence analysis of self adaptive equalizers. IEEE, Trans. Inf. Theory, Vol.IT-30, 2, 1984, 161–176.Google Scholar
  5. 5.
    Heyde, C.C., Hall, D.: Martingale limit theory and its applications. Acad. Press (1980).Google Scholar
  6. 6.
    Kushner, H., Approximation and weak convergence methods for random processes. M.I.T. Press, Cambridge (1984).Google Scholar
  7. 7.
    Kushner, H., Clark, D.S.,: Stochastic approximation methods for constrained and unconstrained systems. Springer (1978).Google Scholar
  8. 8.
    Kushner, H.: Stochastic approximation with discontinuous dynamics and state dependent noise. J. Math. Anal. and Appl. Vol.82, 1981, 527–542.Google Scholar
  9. 9.
    Kushner, H., Shwartz, A.: An invariant measure approach to the convergence of stochastic approximations with state dependent noise. SIAM, 5, Control. Opt. Vol.22, 1, 1984.Google Scholar
  10. 10.
    Ljung, L.,: Analysis of recursive stochastic algorithms. IEEE Trans. Autom. Control, Vol.AC-22, 2, 1977, 551–575.Google Scholar
  11. 11.
    Métivier, M., Priouret, P.: Application of a Kushner and Clark lemma to general classes of stochastic algorithms. IEEE Trans. Inf. Theory, Vol.IT-30, 1984, 140–150.Google Scholar
  12. 12.
    Métivier, M., Priouret, P.: Théorèmes de convergence presque sûre pour une classe d'algorithmes stochastiques. Preprint, Ecole Polytechnique, Palaiseau, 1984.Google Scholar
  13. 13.
    Métivier, M.: Introduction to stochastic approximation and adaptive filtering. Lecture Notes, Dipartimento di Matematica, Univ. di Roma.Google Scholar
  14. 14.
    Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. Stat. Vol.22, 1951, 400–407.Google Scholar
  15. 15.
    Wasan, M.T.: Stochastic approximation. Cambridge Univ. Press (1968).Google Scholar
  16. 16.
    Freidlin, M.I.: Random perturbations of dynamical systems. Springer (1984).Google Scholar

Copyright information

© Springer-Verlag 1987

Authors and Affiliations

  • Michel Metivier
    • 1
  1. 1.Centre de Mathématiques Appliquées Ecole PolytechniquePalaiseau Cedex

Personalised recommendations