Skip to main content

Advertisement

SpringerLink
Log in
Menu
Find a journal Publish with us
Search
Cart
  1. Home
  2. Probability Theory and Related Fields
  3. Article
Martingale transforms with non-atomic limits and stochastic approximation
Download PDF
Download PDF
  • Published: March 1993

Martingale transforms with non-atomic limits and stochastic approximation

  • C. Z. Wei1 

Probability Theory and Related Fields volume 95, pages 103–114 (1993)Cite this article

  • 121 Accesses

  • 4 Citations

  • Metrics details

Summary

A sufficient condition for the limit of a martingale transform to posses a continuous distribution is given. The result is used to show that for a stochastic approximation procedure, if the adjustment rate is too small then it would not converge to the target value a.s. Furthermore, if the adjustment rate is taken to be 1/n as usual but the derivative of the regression function at the target value is 0, then the convergence rate is shown to be logn instead of\(\sqrt n\), the rate obtained when the derivative is non-zero.

Download to read the full article text

Working on a manuscript?

Avoid the common mistakes

References

  1. Barlow, W.J.: Coefficient properties of random variable sequences. Ann. Probab.3, 840–848 (1975)

    Google Scholar 

  2. Burkholder, D.J.: Independent sequences with the Stein property. Ann. Math. Stat.39, 1282–1288 (1968)

    Google Scholar 

  3. Chow, Y.S., Teicher, H.: Probability theory: Independence, interchangeability, martingales. Berlin Heidelberg New York: Springer 1978

    Google Scholar 

  4. Chow, Y.S.: Local convergence of martingales and the law of large numbers. Ann. Math. Stat36, 552–558 (1965)

    Google Scholar 

  5. Feller, W.: An introduction to probability theory and its application, 3rd. edn. New York: Wiley 1968

    Google Scholar 

  6. Kersting, G.: Some results on the asymptotic behavior of the Robbins-Monro Procedure. Bull. Int. Stat. Inst.XLVII, 327–335 (1977)

    Google Scholar 

  7. Lai, T.L., Robbins, H.: Adaptive design in regression and control. Proc. Nat. Acad. Sci. USA75, 586–587 (1978)

    Google Scholar 

  8. Lai, T.L., Robbins, H.: Adaptive design and stochastic approximation. Ann. Stat.7, 1196–1221 (1979)

    Google Scholar 

  9. Lai, T.L., Wei, C.Z.: A note on martingale difference sequences satisfying the local Marcinkiewicz-Zygmund condition. Bull. Inst. Math., Acad. Sin.11, 1–13 (1983a)

    Google Scholar 

  10. Lai, T.L., Wei, C.Z.: Asymptotic properties of general autoregressive models and strong consistency of least-squares estimates of their parameters. J. Multivariate Anal.13, 1–23 (1983b)

    Google Scholar 

  11. Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. Stat.22, 400–407 (1951)

    Google Scholar 

  12. Robbins, H., Siegmund, D.: A convergence theorem for non-negative almost supermartingales and some applications. In: Rustagi, J. (ed.) Optimizing methods in statistics, pp. 233–257. New York: Academic Press 1971

    Google Scholar 

  13. Wei, C.Z.: Multivariate adaptive stochastic approximation. Ann. Stat.15, 1115–1130 (1987)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institute of Statistical Science, Academia Sinica, Taipei, Taiwan, ROC

    C. Z. Wei

Authors
  1. C. Z. Wei
    View author publications

    You can also search for this author in PubMed Google Scholar

Additional information

Research supported by the National Science Council, R.O.C.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Wei, C.Z. Martingale transforms with non-atomic limits and stochastic approximation. Probab. Th. Rel. Fields 95, 103–114 (1993). https://doi.org/10.1007/BF01197340

Download citation

  • Received: 26 June 1991

  • Revised: 22 June 1992

  • Issue Date: March 1993

  • DOI: https://doi.org/10.1007/BF01197340

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

Mathematics Subject Classifications (1980)

  • 60 G 42
  • 62 L 20
Download PDF

Working on a manuscript?

Avoid the common mistakes

Advertisement

Search

Navigation

  • Find a journal
  • Publish with us

Discover content

  • Journals A-Z
  • Books A-Z

Publish with us

  • Publish your research
  • Open access publishing

Products and services

  • Our products
  • Librarians
  • Societies
  • Partners and advertisers

Our imprints

  • Springer
  • Nature Portfolio
  • BMC
  • Palgrave Macmillan
  • Apress
  • Your US state privacy rights
  • Accessibility statement
  • Terms and conditions
  • Privacy policy
  • Help and support

167.114.118.210

Not affiliated

Springer Nature

© 2023 Springer Nature