A Criterion for the Existence of Predictive Complexity for Binary Games

  • Yuri Kalnishkan
  • Vladimir Vovk
  • Michael V. Vyugin
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3244)

Abstract

It is well known that there exists a universal (i.e., optimal to within an additive constant if allowed to work infinitely long) algorithm for lossless data compression (Kolmogorov, Levin). The game of lossless compression is an example of an on-line prediction game; for some other on-line prediction games (such as the simple prediction game) a universal algorithm is known not to exist. In this paper we give an analytic characterisation of those binary on-line prediction games for which a universal prediction algorithm exists.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Zvonkin, A.K., Levin, L.A.: The complexity of finite objects and the development of the concepts of information and randomness by means of the theory of algorithms. Russian Math. Surveys 25, 83–124 (1970)MATHCrossRefMathSciNetGoogle Scholar
  2. 2.
    Vovk, V., Watkins, C.J.H.C.: Universal portfolio selection. In: Proceedings of the 11th Annual Conference on Computational Learning Theory, pp. 12–23 (1998)Google Scholar
  3. 3.
    Cesa-Bianchi, N., Freund, Y., Haussler, D., Helmbold, D.P., Schapire, R.E., Warmuth, M.K.: How to use expert advice. Journal of the ACM 44, 427–485 (1997)MATHCrossRefMathSciNetGoogle Scholar
  4. 4.
    Haussler, D., Kivinen, J., Warmuth, M.K.: Sequential prediction of individual sequences under general loss functions. IEEE Transactions on Information Theory 44, 1906–1925 (1998)MATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Vovk, V.: A game of prediction with expert advice. Journal of Computer and System Sciences 56, 153–173 (1998)MATHCrossRefMathSciNetGoogle Scholar
  6. 6.
    Kalnishkan, Y., Vovk, V., Vyugin, M.V.: Loss functions, complexities, and the Legendre transformation. Theoretical Computer Science 313, 195–207 (2004)MATHCrossRefMathSciNetGoogle Scholar
  7. 7.
    Kalnishkan, Y., Vyugin, M.V.: On the absence of predictive complexity for some games. In: Cesa-Bianchi, N., Numao, M., Reischuk, R. (eds.) ALT 2002. LNCS (LNAI), vol. 2533, pp. 164–172. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  8. 8.
    Kalnishkan, Y., Vyugin, M.V.: Mixability and the existence of weak complexities. In: Kivinen, J., Sloan, R.H. (eds.) COLT 2002. LNCS (LNAI), vol. 2375, pp. 105–120. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  9. 9.
    Li, M., Vitányi, P.: An Introduction to Kolmogorov Complexity and Its Applications. Springer, New York (1997)MATHGoogle Scholar
  10. 10.
    Feller, W.: An Introduction to Probability Theory and Its Applications, 3rd edn., vol. I. John Wiley & Sons, Inc., Chichester (1968)MATHGoogle Scholar
  11. 11.
    Roberts, A.W., Varberg, D.E.: Convex Functions. Academic Press, London (1973)MATHGoogle Scholar
  12. 12.
    Petrov, V.V.: Sums of Independent Random Variables. Springer, Heidelberg (1975)Google Scholar
  13. 13.
    Kalnishkan, Y.: General linear relations among different types of predictive complexity. Theoretical Computer Science 271, 181–200 (2002)MATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Yuri Kalnishkan
    • 1
  • Vladimir Vovk
    • 1
  • Michael V. Vyugin
    • 1
  1. 1.Department of Computer ScienceRoyal Holloway, University of LondonEgham, SurreyUK

Personalised recommendations