Prediction with Expert Advice under Discounted Loss

  • Alexey Chernov
  • Fedor Zhdanov
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6331)


We study prediction with expert advice in the setting where the losses are accumulated with some discounting and the impact of old losses can gradually vanish. We generalize the Aggregating Algorithm and the Aggregating Algorithm for Regression, propose a new variant of exponentially weighted average algorithm, and prove bounds on the cumulative discounted loss.


Loss Function Reproduce Kernel Hilbert Space Expert Advice Convex Game Substitution Function 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Beckenbach, E.F., Bellman, R.: Inequalities. Springer, Berlin (1961)Google Scholar
  2. 2.
    Cesa-Bianchi, N., Lugosi, G.: Prediction, learning, and games. Cambridge University Press, Cambridge (2006)zbMATHCrossRefGoogle Scholar
  3. 3.
    Chaudhuri, K., Freund, Y., Hsu, D.: A parameter-free hedging algorithm. In: Advances in Neural Information Processing Systems, vol. 22, pp. 297–305 (2009)Google Scholar
  4. 4.
    Chernov, A., Kalnishkan, Y., Zhdanov, F., Vovk, V.: Supermartingales in prediction with expert advice. Theoretical Computer Science 411, 2647–2669 (2010); See also: arXiv:1003.2218 [cs.LG]zbMATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Chernov, A., Vovk, V.: Prediction with advice of unknown number of experts. In: Proc. of 26th Conf. on Uncertainty in Artificial Intelligence, pp. 117–125 (2010)Google Scholar
  6. 6.
    Chernov, A., Zhdanov, F.: Prediction with expert advice under discounted loss. Technical report, arXiv:1005.1918v1 [cs.LG] (2010)Google Scholar
  7. 7.
    Freund, Y., Hsu, D.: A new hedging algorithm and its application to inferring latent random variables. Technical report, arXiv:0806.4802v1 [cs.GT] (2008)Google Scholar
  8. 8.
    Gammerman, A., Kalnishkan, Y., Vovk, V.: On-line prediction with kernels and the complexity approximation principle. In: Proc. of 20th Conf. on Uncertainty in Artificial Intelligence, pp. 170–176 (2004)Google Scholar
  9. 9.
    Gardner, E.S.: Exponential smoothing: The state of the art – part II. International Journal of Forecasting 22, 637–666 (2006)CrossRefGoogle Scholar
  10. 10.
    Harville, D.A.: Matrix algebra from a statistician’s perspective. Springer, Heidelberg (1997)zbMATHGoogle Scholar
  11. 11.
    Haussler, D., Kivinen, J., Warmuth, M.: Sequential prediction of individual sequences under general loss functions. IEEE Transactions on Information Theory 44, 1906–1925 (1998)zbMATHCrossRefMathSciNetGoogle Scholar
  12. 12.
    Herbster, M., Warmuth, M.K.: Tracking the best expert. Machine Learning 32, 151–178 (1998)zbMATHCrossRefGoogle Scholar
  13. 13.
    Kalnishkan, Y., Vyugin, M.: The weak aggregating algorithm and weak mixability. Technical report, CLRC-TR-03-01 (2003)Google Scholar
  14. 14.
    Kalnishkan, Y., Vyugin, M.: The weak aggregating algorithm and weak mixability. Journal of Computer and System Sciences 74(8), 1228–1244 (2008)zbMATHCrossRefMathSciNetGoogle Scholar
  15. 15.
    Muth, J.F.: Optimal properties of exponentially weighted forecasts. Journal of the American Statistical Association 55, 299–306 (1960)zbMATHCrossRefGoogle Scholar
  16. 16.
    Schölkopf, B., Smola, A.J.: Learning with kernels: Support Vector Machines, regularization, optimization, and beyond. MIT Press, Cambridge (2002)Google Scholar
  17. 17.
    Sutton, R., Barto, A.: Reinforcement learning: An introduction. MIT Press, Cambridge (1998)Google Scholar
  18. 18.
    Vovk, V.: Aggregating strategies. In: Proc. of 3rd COLT, pp. 371–383 (1990)Google Scholar
  19. 19.
    Vovk, V.: A game of prediction with expert advice. Journal of Computer and System Sciences 56, 153–173 (1998)zbMATHCrossRefMathSciNetGoogle Scholar
  20. 20.
    Vovk, V.: Derandomizing stochastic prediction strategies. Machine Learning 35, 247–282 (1999)zbMATHCrossRefGoogle Scholar
  21. 21.
    Vovk, V.: Competitive on-line statistics. Int. Stat. Review 69, 213–248 (2001)zbMATHGoogle Scholar
  22. 22.
    Vovk, V.: On-line regression competitive with reproducing kernel Hilbert spaces. Technical report, arXiv:cs/0511058 [cs.LG] (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Alexey Chernov
    • 1
  • Fedor Zhdanov
    • 1
  1. 1.Computer Learning Research Centre and Department of Computer ScienceRoyal Holloway, University of LondonEgham, SurreyUK

Personalised recommendations