Journal of Theoretical Probability

, Volume 19, Issue 1, pp 166–189 | Cite as

The Averaged Robbins – Monro Method for Linear Problems in a Banach Space

  • Jürgen Dippon
  • Harro Walk

We consider a recursive method of Robbins–Monro type to solve the linear problem Ax=V in a Banach space. The bounded linear operator A and the vector V are assumed to be observable with some noise only. According to Polyak and Ruppert we use gains converging to zero slower than 1/n and take the average of the iterates as an estimator for the solution of the linear problem. Under weak conditions on the noise processes almost sure and distributional invariance principles are shown.


Averaged stochastic approximation in \(\mathbb{B}\) linear problem strong consistency central limit theorem invariance principle 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Arnold L. (1974). Stochastic Differential Equations; Theory and Applications. Wiley, New YorkMATHGoogle Scholar
  2. 2.
    Billingsley, P. (1999). Convergence of Probability Measures, 2nd ed., Wiley.Google Scholar
  3. 3.
    Bucy, R. S., and Joseph, P. D. (1968). Filtering for Stochastic Processes with Applications to Guidance. Interscience, New YorkMATHGoogle Scholar
  4. 4.
    Dippon J., and Renz J. (1997). Weighted means in stochastic approximation. SIAM J. Control Optim. 35:1811–1827CrossRefMathSciNetMATHGoogle Scholar
  5. 5.
    Györfi, L. (1980). Stochastic approximation from ergodic sample for linear regression. Z. Wahrscheinlichkeitstheorie verw. Gebiete 54:47–55CrossRefMATHGoogle Scholar
  6. 6.
    Györfi L., and Walk H. (1996). On the averaged stochastic approximation for linear regression. SIAM J. Control Optim. 34:31–61CrossRefMathSciNetMATHGoogle Scholar
  7. 7.
    Karamata J. (1938). Einige Sätze über die Rieszschen Mittel. Bull. Acad. Sci. Math. Nat. A 4:121–137Google Scholar
  8. 8.
    Kuelbs J. (1973). The invariance principle for Banach space valued random variables. J. Multivariate Anal. 3:161–172CrossRefMathSciNetMATHGoogle Scholar
  9. 9.
    Knopp K. (1947). Theorie und Anwendung der unendlichen Reihen, 4th ed. Springer, BerlinMATHGoogle Scholar
  10. 10.
    Ljung L., Pflug G., and Walk H. (1992). Stochastic Approximation and Optimization of Random Systems. Birkhäuser, BaselMATHGoogle Scholar
  11. 11.
    Ljung L. and Söderström T. (1983). Theory and Practice of Recursive Identification. MIT Press, CambridgeMATHGoogle Scholar
  12. 12.
    Pechtl A. (1993). Arithmetic means and invariance principles in stochastic approximation. J. Theor. Probab. 6:153–173CrossRefMathSciNetMATHGoogle Scholar
  13. 13.
    Polyak B.T. (1990). New method of stochastic approximation type. Automat. Remote Control 51:937–946MathSciNetMATHGoogle Scholar
  14. 14.
    Polyak B.T., and Juditsky A.B. (1992). Acceleration of stochastic approximation by averaging. SIAM J. Control Optim. 30:838–855CrossRefMathSciNetMATHGoogle Scholar
  15. 15.
    Robbins H., and Monro S. (1951). A stochastic approximation method. Ann. Math. Statist. 22:400–407CrossRefMathSciNetMATHGoogle Scholar
  16. 16.
    Ruppert D. (1991). Stochastic approximation. In Gosh, B. K., and Sen, P. K. (eds.), Handbook of Sequential Analysis, Marcel-Dekker, pp. 503–529Google Scholar
  17. 17.
    Tietz H., and Zeller K. (1997). Tauber-Sätze für bewichtete Mittel. Arch. Math. 68:214–220CrossRefMathSciNetMATHGoogle Scholar
  18. 18.
    Tietz H., and Zeller K. (1998). Tauber-Bedingungen für Verfahren mit Abschnittskonvergenz. Acta Math. Hungar. 81:241–247CrossRefMathSciNetMATHGoogle Scholar
  19. 19.
    Walk H. (1977). An invariance principle for the Robbins–Monro process in a Hilbert space. Z. Wahrscheinlichkeitsth. verw. Gebiete 39:135–150CrossRefMathSciNetMATHGoogle Scholar
  20. 20.
    Walk H. (1980). A functional central limit theorem for martingales in C(K) and its application to sequential estimates. J. Reine Angew. Math. 314:117–135MathSciNetGoogle Scholar
  21. 21.
    Walk H. (1988). Limit behaviour of stochastic approximation processes. Statist. Decisions 6:109–128MathSciNetMATHGoogle Scholar
  22. 22.
    Walk H., and Zsidó L. (1989). Convergence of the Robbins–Monro method for linear problems in a Banach space. J. Math. Anal. Appl. 139:152–177CrossRefMathSciNetMATHGoogle Scholar
  23. 23.
    Yin G.G. (1991). On extensions of Polyak’s averaging approach to stochastic approximation. Stoch. Stoch. Rep. 36:245–264MATHGoogle Scholar
  24. 24.
    Yin G.G., and Zhu Y. (1992). Averaging procedures in adaptive filtering: an efficient approach. IEEE Trans. Automat. Contr. 37:466–475CrossRefMathSciNetMATHGoogle Scholar

Copyright information

© Springer Science+Business Media, Inc. 2006

Authors and Affiliations

  1. 1.Fachbereich MathematikUniversität StuttgartStuttgartGermany

Personalised recommendations