Skip to main content
SpringerLink
Log in

New insights into Witsenhausen’s counterexample

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

Abstract

The accuracies of certain suboptimal solutions to the famous and still unsolved optimization problem known as “Witsenhausen’s counterexample” are investigated. The differences between the corresponding suboptimal values of the Witsenhausen functional and its optimum are estimated, too. The results give insights into the effectiveness of certain approaches proposed in the literature to face this hard optimization problem and into numerical results obtained by some researchers.

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. Alessandri A., Sanguineti M.: Optimization of approximating networks for optimal fault diagnosis. Optim. Methods Softw. 20, 235–260 (2005)

    Article  MathSciNet  Google Scholar 

  2. Baglietto M., Parisini T., Zoppoli R.: Numerical solutions to the Witsenhausen counterexample by approximating networks. IEEE Trans. Autom. Control 46, 1471–1477 (2001)

    Article  MathSciNet  MATH  Google Scholar 

  3. Barron, A.R.: Neural net approximation. In: Narendra, K. (ed.) Proceedings of 7th Yale Workshops on Adaptive and Learning Systems, pp. 69–72. Yale University Press (1992)

  4. Barron A.R.: Universal approximation bounds for superpositions of a sigmoidal function. IEEE Trans. Inf. Theory 39, 930–945 (1993)

    Article  MathSciNet  MATH  Google Scholar 

  5. Bennet K.P., Mangasarian O.L.: Neural network training via linear programming. In: Pardalos, P.M. (eds) Advances in Optimization and Parallel Computing, pp. 56–67. North-Holland, Amsterdam (1992)

    Google Scholar 

  6. Chu K.C.: Team decision theory and information structures in optimal control, part II. IEEE Trans. Autom. Control 17, 22–28 (1972)

    Article  MATH  Google Scholar 

  7. Daniel J.W.: The Approximate Minimization of Functionals. Prentice-Hall, Englewood Cliffs (1971)

    MATH  Google Scholar 

  8. Darken, C., Donahue, M., Gurvits, L., Sontag, E.: Rate of approximation results motivated by robust neural network learning. In: Proceedings of 6th Annual ACM Conference on Computational Learning Theory, pp. 303–309. The Association for Computing Machinery, New York (1993)

  9. Deng M., Ho Y.C.: An ordinal optimization approach to optimal control problems. Automatica 35, 331–338 (1999)

    Article  MathSciNet  MATH  Google Scholar 

  10. Giulini S., Sanguineti M.: Approximation schemes for functional optimization problems. J. Optim. Theory Appl. 140, 33–54 (2009)

    Article  MathSciNet  MATH  Google Scholar 

  11. Gnecco, G., Sanguineti, M.: Suboptimal solutions to network team optimization problems. In: CD-Proc. Int. Network Optimization Conference (INOC) (2009)

  12. Gnecco, G., Sanguineti, M.: Smooth optimal decision strategies for static team optimization problems and their approximations. In: Lecture Notes in Computer Science, vol. 5901, pp. 440–451. Springer, Berlin (2010)

  13. Gnecco G., Sanguineti M.: Team optimization problems with Lipschitz continuous strategies. Optim. Lett. 5, 333–346 (2011)

    Article  MathSciNet  MATH  Google Scholar 

  14. Grover P., Sahai A.: Witsenhausen’s counterexample as assisted interference suppression. Int. J. Syst. Control Commun. 2, 197–237 (2010)

    Article  Google Scholar 

  15. Grover, P., Sahai, A.: Is Witsenhausen’s counterexample a relevant toy? In: Proceedings of 49th IEEE Conference on Decision and Control (CDC), Atlanta, GA, USA, pp. 585–590, December 15–17, 2010

  16. Grover, P., Sahai, A., Park, S.Y.: The finite-dimensional Witsenhausen counterexample. In: Proc. 7th Int. Symp. on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt), June 23–27, Seoul, Korea (2009)

  17. Haykin S.: Neural Networks: A Comprehensive Foundation, 2nd edn. Prentice-Hall, Englewood Cliffs (1998)

    Google Scholar 

  18. Ho, Y.C.: Review of the Witsenhausen problem. In: Proceedings of 47th IEEE Conference on Decision and Control (CDC), pp. 1611–1613 (2008)

  19. Ho Y.C., Chu K.C.: Team decision theory and information structures in optimal control problems, part I. IEEE Trans. Autom. Control 17, 15–22 (1972)

    Article  MathSciNet  MATH  Google Scholar 

  20. Jones L.K.: A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training. Ann. Stat. 20, 608–613 (1992)

    Article  MATH  Google Scholar 

  21. Juditsky A., Hjalmarsson H., Benveniste A., Delyon B., Ljung L., Sjöberg J., Zhang Q.: Nonlinear black-box models in system identification: mathematical foundations. Automatica 31, 1725–1750 (1995)

    Article  MATH  Google Scholar 

  22. Kůrková V., Kainen P.C., Kreinovich V.: Estimates of the number of hidden units and variation with respect to half-spaces. Neural Netw. 10, 1061–1068 (1997)

    Article  Google Scholar 

  23. Kůrková V., Sanguineti M.: Error estimates for approximate optimization by the extended Ritz method. SIAM J. Optim. 15, 261–287 (2005)

    Google Scholar 

  24. Kůrková V., Sanguineti M.: Learning with generalization capability by kernel methods of bounded complexity. J. Complex. 21, 350–367 (2005)

    Article  MATH  Google Scholar 

  25. Kůrková V., Sanguineti M.: Approximate minimization of the regularized expected error over kernel models. Math. Oper. Res. 33, 747–756 (2008)

    Article  MathSciNet  MATH  Google Scholar 

  26. Kůrková V., Sanguineti M.: Geometric upper bounds on rates of variable-basis approximation. IEEE Trans. Inf. Theory 54, 5681–5688 (2008)

    Article  Google Scholar 

  27. Kainen P.C., Kůrková V., Sanguineti M.: Complexity of Gaussian radial-basis networks approximating smooth functions. J. Complex. 25, 63–74 (2009)

    Article  MATH  Google Scholar 

  28. Kim K.H., Roush F.W.: Team Theory. Ellis Horwood Limited, Chichester (1988)

    Google Scholar 

  29. Kolmogorov A.N., Fomin S.V.: Introductory Real Analysis. Dover, New York (1970)

    MATH  Google Scholar 

  30. Lee J.T., Lau E., Ho Y.C.: The Witsenhausen counterexample: a hierarchical search approach for nonconvex optimization problems. IEEE Trans. Autom. Control 46, 382–397 (2001)

    Article  MathSciNet  MATH  Google Scholar 

  31. Li, N., Marden, J.R., Shamma, J.S.: Learning approaches to the Witsenhausen counterexample from a view of potential games. In: Proceedings of 48th IEEE Conference on Decision and Control (CDC), pp. 157–162 (2009)

  32. Murphey, R., Pardalos, P.M. (eds): Cooperative Control and Optimization. Kluwer, Dordrecht (2002)

    Google Scholar 

  33. Papadimitriou C.H., Tsitsiklis J.N.: Intractable problems in control theory. SIAM J. Control Optim. 24, 639–654 (1986)

    Article  MathSciNet  MATH  Google Scholar 

  34. Pisier, G.: Remarques sur un résultat non publié de B. Maurey. In: Séminaire d’Analyse Fonctionnelle 1980–81, vol. I, no. 12. École Polytechnique, Centre de Mathématiques, Palaiseau, France (1981)

  35. Sanguineti M.: Universal approximation by ridge computational models: a survey. Open Appl. Math. J. 2, 31–58 (2008)

    Article  MathSciNet  Google Scholar 

  36. Sjöberg J., Zhang Q., Ljung L., Benveniste A., Glorennec P.-Y., Delyon B., Hjalmarsson H., Juditsky A.: Nonlinear black-box modeling in system identification: a unified overview. Automatica 31, 1691–1724 (1995)

    Article  MATH  Google Scholar 

  37. Witsenhausen H.S.: A counterexample in stochastic optimum control. SIAM J. Control Optim. 6, 131–147 (1968)

    Article  MathSciNet  MATH  Google Scholar 

  38. Witsenhausen H.S.: Equivalent stochastic control problems. Math. Control Signals Syst. 1, 3–11 (1988)

    Article  MathSciNet  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Communications, Computer, and System Sciences (DIST), University of Genoa, Via Opera Pia 13, 16145, Genoa, Italy

    Giorgio Gnecco & Marcello Sanguineti

Authors
  1. Giorgio Gnecco
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Marcello Sanguineti
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Marcello Sanguineti.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Gnecco, G., Sanguineti, M. New insights into Witsenhausen’s counterexample. Optim Lett 6, 1425–1446 (2012). https://doi.org/10.1007/s11590-011-0339-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11590-011-0339-6

Keywords

Search

Navigation