The Follow Perturbed Leader Algorithm Protected from Unbounded One-Step Losses

  • Vladimir V. V’yugin
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5809)

Abstract

In this paper the sequential prediction problem with expert advice is considered for the case when the losses of experts suffered at each step can be unbounded. We present some modification of Kalai and Vempala algorithm of following the perturbed leader where weights depend on past losses of the experts. New notions of a volume and a scaled fluctuation of a game are introduced. We present an algorithm protected from unrestrictedly large one-step losses. This algorithm has the optimal performance in the case when the scaled fluctuations of one-step losses of experts of the pool tend to zero.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Cesa-Bianchi, N., Mansour, Y., Stoltz, G.: Improved second-order bounds for prediction with expert advice. Machine Learning 66(2-3), 321–352 (2007)CrossRefMATHGoogle Scholar
  2. 2.
    Allenberg, C., Auer, P., Gyorfi, L., Ottucsak, G.: Hannan consistency in on-Line learning in case of unbounded losses under partial monitoring. In: Balcázar, J.L., Long, P.M., Stephan, F. (eds.) ALT 2006. LNCS (LNAI), vol. 4264, pp. 229–243. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  3. 3.
    Hannan, J.: Approximation to Bayes risk in repeated plays. In: Dresher, M., Tucker, A.W., Wolfe, P. (eds.) Contributions to the Theory of Games, vol. 3, pp. 97–139. Princeton University Press, Princeton (1957)Google Scholar
  4. 4.
    Hutter, M., Poland, J.: Prediction with expert advice by following the perturbed leader for general weights. In: Ben-David, S., Case, J., Maruoka, A. (eds.) ALT 2004. LNCS (LNAI), vol. 3244, pp. 279–293. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  5. 5.
    Kalai, A., Vempala, S.: Efficient algorithms for online decisions. In: Schölkopf, B., Warmuth, M.K. (eds.) COLT/Kernel 2003. LNCS (LNAI), vol. 2777, pp. 26–40. Springer, Heidelberg (2003); Extended version in Journal of Computer and System Sciences 71, 291–307 (2005)CrossRefGoogle Scholar
  6. 6.
    Littlestone, N., Warmuth, M.K.: The weighted majority algorithm. Information and Computation 108, 212–261 (1994)MathSciNetCrossRefMATHGoogle Scholar
  7. 7.
    Lugosi, G., Cesa-Bianchi, N.: Prediction, Learning and Games. Cambridge University Press, New York (2006)MATHGoogle Scholar
  8. 8.
    Petrov, V.V.: Sums of independent random variables. Ergebnisse der Mathematik und ihrer Grenzgebiete, Band 82. Springer, Heidelberg (1975)Google Scholar
  9. 9.
    Poland, J., Hutter, M.: Defensive universal learning with experts. For general weight. In: Jain, S., Simon, H.U., Tomita, E. (eds.) ALT 2005. LNCS (LNAI), vol. 3734, pp. 356–370. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  10. 10.
    Shiryaev, A.N.: Probability. Springer, Berlin (1980)MATHGoogle Scholar
  11. 11.
    Vovk, V.G.: Aggregating strategies. In: Fulk, M., Case, J. (eds.) Proceedings of the 3rd Annual Workshop on Computational Learning Theory, San Mateo, CA, pp. 371–383. Morgan Kaufmann, San Francisco (1990)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Vladimir V. V’yugin
    • 1
  1. 1.Institute for Information Transmission ProblemsRussian Academy of SciencesMoscow GSP-4Russia

Personalised recommendations