Skip to main content
SpringerLink
Log in

Analysis of practical step size selection in stochastic approximation algorithms

  • Published:
Annals of Operations Research Aims and scope Submit manuscript

Abstract

For many popular stochastic approximation algorithms, such as the stochastic gradient method and the simultaneous perturbation stochastic approximation method, the practical gain sequence selection is different from the optimal selection, that is theoretically derived from asymptotical performance. We provide formal justification for the reasons why we choose such gain sequence in practice.

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

Fig. 1
Fig. 2

Similar content being viewed by others

References

  • Bangerth, W., Klie, H., Matossian, V., Parashar, M., & Wheeler, M. F. (2006). An autonomic reservoir framework for the stochastic optimization of well placement. Cluster Computing, 8(4), 255–269.

    Article  Google Scholar 

  • Cao, X. (2011). Preliminary results on non-bernoulli distribution of perturbations for simultaneous perturbation stochastic approximation. In Proceedings of the American control conference, 29 June–1 July 2011, San Francisco, CA (pp. 2669–2670) (paper ThB10.6).

  • Fu, M. C. (1994). Optimization via simulation: A review. Annals of Operations Research, 53, 199–247.

    Article  Google Scholar 

  • Horn, R. A., & Johnson, C. R. (1985). Matrix analysis. Cambridge: Cambridge University Press.

    Book  Google Scholar 

  • Hutchison, D. W., & Spall, J. C. (2009). Stopping small-sample stochastic approximation. In Proceedings of American control conference, St. Louis, MO, 10–12 June, 2009.

  • Kushner, H., & Yin, G. (2003). Stochastic approximation and recursive algorithms and application. New York: Springer.

    Google Scholar 

  • Maryak, J. L., & Spall, J. C. (2005). Simultaneous perturbation optimization for efficient image restoration. IEEE Transactions on Aerospace and Electronic Systems, 41(1), 356–361.

    Article  Google Scholar 

  • Rubinstein, R. Y., & Kroese, D. P. (2007). Simulation and the Monte Carlo method. Wiley series in probability and statistics.

  • Schwartz, J. D., Wang, W., & Rivera, D. E. (2006). Simulation-based optimization of process control policies for inventory management in supply chains. Automatica, 42(8), 1311–1320.

    Article  Google Scholar 

  • Spall, J. C. (1992). Multivariate stochastic approximation using simultaneous perturbation gradient approximation. IEEE Transactions on Automatic Control, 37(3), 332–341.

    Article  Google Scholar 

  • Spall, J. C. (1998). Implementation of the simultaneous perturbation algorithm for stochastic optimization. IEEE Transactions on Aerospace and Electronic Systems, 34(3), 817–823.

    Article  Google Scholar 

  • Spall, J. C. (2003). Introduction to stochastic search and optimization: Estimation, simulation, and control. Hoboken, NJ: Wiley.

    Book  Google Scholar 

  • Spall, J. C. (2012). Cyclic seesaw process for optimization and identification. Journal of Optimization Theory and Applications, 154(1), 187–208.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Applied Mathematics and Statistics, Johns Hopkins University, Baltimore, MD, USA

    Qi Wang

Authors
  1. Qi Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Qi Wang.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, Q. Analysis of practical step size selection in stochastic approximation algorithms. Ann Oper Res 229, 759–769 (2015). https://doi.org/10.1007/s10479-015-1785-9

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10479-015-1785-9

Keywords

Search

Navigation