Advertisement

On a Class of Stochastic Approximation Processes

  • Burgess Davis
  • Renming Song
Chapter
Part of the Selected Works in Probability and Statistics book series (SWPS)

Abstract

We are concerned with the asymptotic behavior of stochastic approximation processes of the Robbins-Monro type [9], the Kiefer-Wolfowitz type [7], and related types. Our main interest is establishing the asymptotic normality, under appropriate conditions, of processes of certain kinds. However, a number of results on convergence with probability one are also obtained as immediate consequences of a theorem needed in the work on asymptotic normality. Our results contain and extend some of the results in this area reported by Blum [1], Chung [3], Hodges and Lehmann [5], and others. In addition, we establish a number of results for cases not previously investigated. For instance, we show that the Kiefer-Wolfowitz processes are asymptotically normal under quite general conditions. The rapidity of convergence depends on the amount that the function M(of Corollary 3.2) departs from symmetry in the neighborhood of the location of the maximum. We give results on convergence with probability one and asymptotic normality of stochastic approximation processes useful in connection with the problem of finding the location of the point of inflection of a function. For all cases in which we establish asymptotic normality we also show how the unknown quantities in the variance of the limiting normal distribution can be estimated. These results make possible the construction of asymptotic confidence intervals free of unknowns. Other results, too detailed to be summarized here, are established which also might be of interest in practical applications.

Keywords

Regression Function Number Sequence Independent Random Variable Asymptotic Normality Stochastic Approximation 
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.
    J. R. Blum"Approximation methods which converge with probability one," Ann. Math. Stat., Vol. 25 (1954), pp. 382-386.MATHCrossRefGoogle Scholar
  2. 2.
    D. L. Burkholder, "On a certain class of stochastic approximation processes," un- published thesis, University of North Carolina, 1955.Google Scholar
  3. 3.
    K. L. Chung"On a stochastic approximation method," Ann. Math. Stat., Vol. 25 (1954), pp. 463-83.MATHCrossRefGoogle Scholar
  4. 4.
    H. Cramer, Mathematical Methods of Statistics, Princeton University Press, 1946.Google Scholar
  5. 5.
    J. L. Hodges, Jr., andE. L. Lehmann, "Twoapproximations to the Robbins-Monro process," Proceedings of the Third Berkeley Symposium on Mathematical Statis- tics and Probability, University of California Press, to be published.Google Scholar
  6. 6.
    G. Kallianpur"A note on the Robbins-Monro stochastic approximation method," Ann. Math. Stat., Vol. 25 (1954), pp. 386-388.MATHCrossRefMathSciNetGoogle Scholar
  7. 7.
    J. Kiefer andJ. Wolfowitz"Stochastic estimation of the maximum of a regression function," Ann. Math. Stat., Vol. 23 (1952), pp. 462-466.MATHCrossRefMathSciNetGoogle Scholar
  8. 8.
    M. Loève, "On almost sure convergence," Proceedings of the Second Berkeley Sym- posium on Mathematical Statistics and Probability, University of California Press, 1951, pp. 279-303.Google Scholar
  9. 9.
    H. Bobbins andS. Monro"A stochastic approximation method" Ann. Math. Stat., Vol. 22 (1951), pp. 400-407.CrossRefGoogle Scholar
  10. 10.
    L. Schmetterer"Bemerkungen zum Verfahren der stochastischen Iteration," Österreich. Ing.-Arch., Vol. 7 (1953), pp. 111-117.MATHMathSciNetGoogle Scholar
  11. 11.
    L. Schmetterer"Zum Sequentialverfahren von Robbins und Monro," Monatsh. Math., Vol. 58 (1954), pp. 33-37.MATHCrossRefMathSciNetGoogle Scholar
  12. 12.
    J. Wolfowitz"On the stochastic approximation method of Robbins and Monro," Ann. Math. Stat., Vol. 23 (1952), pp. 457-461.MATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  1. 1.Department of Mathematics and Department of StatisticsPurdue UniversityWest LafayetteUSA
  2. 2.Department of MathematicsUniversity of IllinoisUrbanaUSA

Personalised recommendations