Advertisement

An Efficient Stochastic Approximation Algorithm for Stochastic Saddle Point Problems

  • Arkadi Nemirovski
  • Reuven Y. Rubinstein
Part of the International Series in Operations Research & Management Science book series (ISOR, volume 46)

Abstract

We show that Polyak’s (1990) stochastic approximation algorithm with averaging originally developed for unconstrained minimization of a smooth strongly convex objective function observed with noise can be naturally modified to solve convex-concave stochastic saddle point problems. We also show that the extended algorithm, considered on general families of stochastic convex-concave saddle point problems, possesses a rate of convergence unimprovable in order in the minimax sense. We finally present supporting numerical results for the proposed algorithm.

Keywords

Modeling Uncertainty Stochastic Approximation Search Point Saddle Point Problem Minimax Problem 
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. Asmussen, S. and R. Y. Rubinstein. (1992). “The efficiency and heavy traffic properties of the score function method in sensitivity analysis of queuing models”, Advances of Applied Probability, 24(1), 172–201.CrossRefGoogle Scholar
  2. Ermoliev, M. (1969). “On the method of generalized stochastic gradients and quasi-Fejer sequences”, Cybernetics, 5(2), 208–220.MathSciNetCrossRefGoogle Scholar
  3. Ermoliev, Y.M. and A. A. Gaivoronski. (1992). “Stochastic programming techniques for optimization of discrete event systems”, Annals of Operations Research, 39, 1–41.MathSciNetCrossRefGoogle Scholar
  4. Kleinrock, L. (1975). Queuing Systems, Vols. I and II, Wiley, New York.zbMATHGoogle Scholar
  5. Kushner, H.I. and D. S. Clarke. (1978). Stochastic Approximation Methods for Constrained and Unconstrained Systems, Springer-Verlag, Applied Math. Sciences, Vol. 26.CrossRefGoogle Scholar
  6. L’Ecuyer, P., N. Giroux, and P.W. Glynn. (1994). “Stochastic optimization by simulation: Numerical experiments for the M/M/1 queue in steady-state”, Management Science, 40, 1245–1261.CrossRefGoogle Scholar
  7. Ljung, L., G. Pflug, and H. Walk.(1992). Stochastic Approximation and Optimization of Stochastic Systems. Birkhaus Verlag, Basel.CrossRefGoogle Scholar
  8. Nemirovski, A. and D. Yudin. (1978). “On Cesàro’s convergence of the gradient descent method for finding saddle points of convex-concave functions” Doklady Akademii Nauk SSSR, Vol. 239,No. 4, (in Russian; translated into English as Soviet Math. Doklady).Google Scholar
  9. Nemirovski, A. and D. Yudin. (1983). Problem Complexity and Method Efficiency in Optimization, J. Wiley & Sons.Google Scholar
  10. Pflug, G. Ch. (1992). “Optimization of simulated discrete event processes”. Annals of Operations Research, 39, 173–195.MathSciNetCrossRefGoogle Scholar
  11. Polyak, B.T. (1990). “New method of stochastic approximation type”, Automat. Remote Control, 51, 937–946.MathSciNetzbMATHGoogle Scholar
  12. Rockafellar, R.T. (1970). Convex Analysis, Princeton University Press.Google Scholar
  13. Rubinstein, R.Y. and A. Shapiro. (1993). Discrete Event Systems: Sensitivity Analysis and Stochastic Optimization Via the Score Function Method, to be published by John Wiley & Sons.Google Scholar
  14. Shapiro, A. (1996). “Simulation based optimization—Convergence analysis and statistical inference”, Stochastic Models, to appear.MathSciNetCrossRefGoogle Scholar
  15. Tsypkin Ya.Z. (1970). Adaptation and Learning in Automatic Systems, Academic Press, New York.zbMATHGoogle Scholar

Copyright information

© Springer Science + Business Media, Inc. 2002

Authors and Affiliations

  • Arkadi Nemirovski
  • Reuven Y. Rubinstein
    • 1
  1. 1.Faculty of Industrial Engineering and ManagementTechnion—Israel Institute of TechnologyHaifaIsrael

Personalised recommendations