Skip to main content
SpringerLink
Log in

A combined direction stochastic approximation algorithm

  • Original Paper
  • Published:
Optimization Letters Aims and scope Submit manuscript

Abstract

The stochastic approximation problem is to find some root or minimum of a nonlinear function in the presence of noisy measurements. The classical algorithm for stochastic approximation problem is the Robbins-Monro (RM) algorithm, which uses the noisy negative gradient direction as the iterative direction. In order to accelerate the classical RM algorithm, this paper gives a new combined direction stochastic approximation algorithm which employs a weighted combination of the current noisy negative gradient and some former noisy negative gradient as iterative direction. Both the almost sure convergence and the asymptotic rate of convergence of the new algorithm are established. Numerical experiments show that the new algorithm outperforms the classical RM algorithm.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

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

    Article  MATH  MathSciNet  Google Scholar 

  2. Fabian V.: On asymptotic normality in stochastic approximation. Ann. Math. Stat. 39, 1327–1332 (1968)

    Article  MATH  MathSciNet  Google Scholar 

  3. Wasan, M.: Stochastic Approximation. Cambridge University Press (1970).

  4. Nevel’son M.B., Khas’minskij R.Z.: Stochastic Approximation and Recursive Estimation. American Mathematical Society, Providence (1973)

    MATH  Google Scholar 

  5. Blum J.R.: Multidimensional stochastic approximation methods. Ann. Math. Stat. 25, 737–744 (1954)

    Article  MATH  Google Scholar 

  6. Kiefer J., Wolfowitz J.: Stochastic estimation of the modulus of a regression function. Ann. Math. Stat. 23, 462–466 (1952)

    Article  MATH  MathSciNet  Google Scholar 

  7. Kushner H.J., Clark D.S.: Stochastic Approximation for Constrained and Unconstrained Systems. Springer (1978).

  8. Spall J.C.: Multivariate stochastic approximation using a simultanoues perturbation gradient approximation. IEEE Trans. Automat. Contr. 37, 332–341 (1992)

    Article  MATH  MathSciNet  Google Scholar 

  9. Kesten H.: Accelerated stochastic approximation. Ann. Math. Stat. 29, 41–59 (1958)

    Article  MATH  MathSciNet  Google Scholar 

  10. Delyon B., Juditsky A.: Accelerated stochastic approximation. SIAM J. Optim. 3, 868–881 (1993)

    Article  MATH  MathSciNet  Google Scholar 

  11. Spall, J.C.: Introduction to Stochastic Search and Optimization. Wiley (2003).

  12. Dai, Y.H., Yuan, Y.: Nonlinear Conjugate Gradient Methods, Shanghai Scientific and Technical Publishers (2000). (in Chinese)

  13. Bertsekas D.P., Tsitsiklis J.N.: Gradient convergence in gradient methods with errors. SIAM J. Optim. 10, 627–642 (2003)

    Article  MathSciNet  Google Scholar 

  14. Moré J.J., Garbow B.S., Hillstrom K.E.: Testing unconstrained optimization software. ACM Trans. Math. Softw. 7, 17–41 (1981)

    Article  MATH  Google Scholar 

  15. Spall J.C.: Adaptive stochastic approximation by the simultaneous perturbation method. IEEE Trans. Automat. Contr. 45, 1839–1853 (2000)

    Article  MATH  MathSciNet  Google Scholar 

  16. Schraudolph, N.N., Graepel, T.: Combining conjugate direction methods with stochastic approximation of gradients. In: Proceedings of the 9th International Workshop on Artificial Intelligence and Statistics, Key West, FL, pp. 7–13 (2002)

  17. Xu Z., Dai Y.H.: A stochastic approximation frame algorithm with adaptive directions. Numer. Math. Theory Methods Appl. 1, 460–474 (2008)

    MATH  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Mathematics, Science of College, Shanghai University, 200444, Shanghai, People’s Republic of China

    Zi Xu

Authors
  1. Zi Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zi Xu.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Xu, Z. A combined direction stochastic approximation algorithm. Optim Lett 4, 117–129 (2010). https://doi.org/10.1007/s11590-009-0139-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11590-009-0139-4

Keywords

Search

Navigation