Advertisement

Ensembles and Multiple Classifiers: A Game-Theoretic View

  • Nicolò Cesa-Bianchi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6713)

Aggregating Strategies

The study of multiple classifier systems is a fundamental topic in modern machine learning. However, early work on aggregation of predictors can be traced back to the Fifties, in the area of game theory. At that time, the pioneering work of James Hannan [11] and David Blackwell [2] laid down the foundations of repeated game theory. In a nutshell, a repeated game is the game-theoretic interpretation of learning. In games played once, lacking any information about the opponent, the best a player can do is to play the minimax strategy (the best strategy against the worst possible opponent). In repeated games, by examining the history of past opponent moves, the player acquires information about the opponent’s behavior and can adapt to it, in order to achieve a better payoff than that guaranteed by the minimax strategy.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Azoury, K.S., Warmuth, M.K.: Relative loss bounds for on-line density estimation with the exponential family of distributions. Machine Learning 43(3), 211–246 (2001)CrossRefzbMATHGoogle Scholar
  2. 2.
    Blackwell, D.: An analog of the minimax theorem for vector payoffs. Pacific Journal of Mathematics 6, 1–8 (1956)CrossRefzbMATHGoogle Scholar
  3. 3.
    Cavallanti, G., Cesa-Bianchi, N., Gentile, C.: Linear algorithms for online multitask classification. Journal of Machine Learning Research 11, 2597–2630 (2010)zbMATHGoogle Scholar
  4. 4.
    Cesa-Bianchi, N., Conconi, A., Gentile, C.: On the generalization ability of on-line learning algorithms. IEEE Transactions on Information Theory 50(9), 2050–2057 (2004)CrossRefzbMATHGoogle Scholar
  5. 5.
    Cesa-Bianchi, N., Freund, Y., Helmbold, D.P., Haussler, D., Schapire, R., Warmuth, M.K.: How to use expert advice. Journal of the ACM 44(3), 427–485 (1997)CrossRefzbMATHGoogle Scholar
  6. 6.
    Cesa-Bianchi, N., Long, P.M., Warmuth, M.K.: Worst-case quadratic loss bounds for a generalization of the Widrow-Hoff rule. In: Proceedings of the 6th Annual ACM Workshop on Computational Learning Theory, pp. 429–438. ACM Press, New York (1993)Google Scholar
  7. 7.
    Cover, T.: Behaviour of sequential predictors of binary sequences. In: Proceedings of the 4th Prague Conference on Information Theory, Statistical Decision Functions and Random Processes, pp. 263–272. Publishing house of the Czechoslovak Academy of Sciences (1965)Google Scholar
  8. 8.
    Cover, T.: Universal portfolios. Mathematical Finance 1, 1–29 (1991)CrossRefzbMATHGoogle Scholar
  9. 9.
    Freund, Y., Schapire, R.: Game theory, on-line prediction and boosting. In: Proceedings of the 9th Annual Conference on Computational Learning Theory. ACM Press, New York (1996)Google Scholar
  10. 10.
    Gentile, C.: The robustness of the p-norm algorithms. Machine Learning 53(3), 265–299 (2003)CrossRefzbMATHGoogle Scholar
  11. 11.
    Hannan, J.: Approximation to Bayes risk in repeated play. Contributions to the theory of games 3, 97–139 (1957)zbMATHGoogle Scholar
  12. 12.
    Jie, L., Orabona, F., Fornoni, M., Caputo, B., Cesa-Bianchi, N.: OM-2: An online multi-class multi-kernel learning algorithm. In: Proceedings of the 4th IEEE Online Learning for Computer Vision Workshop. IEEE Press, Los Alamitos (2007)Google Scholar
  13. 13.
    Kakade, S., Shalev-Shwartz, S., Tewari, A.: On the duality of strong convexity and strong smoothness: Learning applications and matrix regularization (2009)Google Scholar
  14. 14.
    Littlestone, N.: Learning quickly when irrelevant attributes abound: a new linear-threshold algorithm. Machine Learning 2(4), 285–318 (1988)Google Scholar
  15. 15.
    Littlestone, N., Warmuth, M.K.: The weighted majority algorithm. Information and Computation 108, 212–261 (1994)CrossRefzbMATHGoogle Scholar
  16. 16.
    Novikoff, A.B.J.: On convergence proofs of Perceptrons. In: Proceedings of the Symposium on the Mathematical Theory of Automata vol. XII, pp. 615–622 (1962)Google Scholar
  17. 17.
    Vovk, V.: Competitive on-line statistics. International Statistical Review 69, 213–248 (2001)CrossRefzbMATHGoogle Scholar
  18. 18.
    Vovk, V.G.: Aggregating strategies. In: Proceedings of the 3rd Annual Workshop on Computational Learning Theory, pp. 372–383 (1990)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Nicolò Cesa-Bianchi
    • 1
  1. 1.DSIUniversità degli Studi di MilanoItaly

Personalised recommendations