Minimizing regret with label efficient prediction

IEEE Transactions on Information Theory

Volumn 51, Issue 6, 2005, Pages 2152-2162

  Cesa Bianchi, Nicolò ^a   Lugosi, Gábor ^b   Stoltz, Gilles ^c  

^a UNIVERSITY OF MILAN   (Italy)

^b UNIVERSITAT POMPEU FABRA   (Spain)

^c ECOLE NORMALE SUPÉRIEURE   (France)

Author keywords

Individual sequences; Label efficient prediction; On line learning; Prediction with expert advice

Indexed keywords

FORECASTING; MATHEMATICAL MODELS; PROBABILITY DISTRIBUTIONS; RANDOM PROCESSES; SET THEORY;

INDIVIDUAL SEQUENCES; LABEL EFFICIENT PREDICTION; ON-LINE LEARNING; PREDICTION WITH EXPERT ADVICE;

GAME THEORY;

EID: 20544462399     PISSN: 00189448     EISSN: None     Source Type: Journal    
DOI: 10.1109/TIT.2005.847729     Document Type: Article

References (22)

1. J. Hannan, "Approximation to Bayes risk in repeated play," Contributions to the Theory of Games, vol. 3, pp. 97-139, 1957.
2. D. Blackwell, "Controlled random walks," in Proc. Int. Congress of Mathematicians, 1954, vol. III, Amsterdam, The Netherlands, 1956, pp. 336-338.
3. N. Cesa-Bianchi, Y. Freund, D. Helmbold, D. Haussler, R. Schapire, and M. Warmuth, "How to use expert advice," J. ACM, vol. 44, no. 3, pp. 427-485, 1997.
4. D. Helmbold and S. Panizza, "Some label efficient learning results," in Proc. 10th Annu. Conf. Computational Learning Theory, Nashville, TN, Jul. 1997, pp. 218-230.
5. J.-F. Mertens, S. Sorin, and S. Zamir, "Repeated Games," Louvain-la-Neuve, CORE discussion paper, no. 9420,9421,9422, 1994.
6. A. Rustichini, "Minimizing regret: The general case," Games and Economic Behavior, vol. 29, pp. 224-243, 1999.
7. A. Piccolboni and C. Schindelhauer, "Discrete prediction games with arbitrary feedback and loss," in Proc. 14th Annu. Conf. Computational Learning Theory, Amsterdam, The Netherlands, Jul. 2001, pp. 208-223.
8. S. Mannor and N. Shimkin, "On-line learning with imperfect monitoring," in Proc. 16th Annu. Conf. Learning Theory, New York, 2003, pp. 552-567.
9. N. Cesa-Bianchi, G. Lugosi, and G. Stoltz, "Regret minimization under partial monitoring," unpublished manuscript, 2004.
10. A. Baños, "On pseudo-games," Ann. Math. Statist., vol. 39, pp. 1932-1945, 1968.
11. N. Megiddo, "On repeated games with incomplete information played by non-Bayesian players," International J. Game Theory, vol. 9, pp. 157-167, 1980.
12. D. Foster and R. Vohra, "Asymptotic calibration," Biometrika, vol. 85, pp. 379-390, 1998.
13. S. Hart and A. Mas-Colell, "A reinforcement procedure leading to correlated equilibrium," in Economic Essays: A Festschriftfor Werner Hilden-brand, G. Debreu, W. Neuefeind, and W. Trockel, Eds. New York: Springer-Verlag, 2002, pp. 181-200.
14. P. Auer, N. Cesa-Bianchi, Y. Freund, and R. Schapire, "The nonstochastic multiarmed bandit problem," SIAM J. Computing, vol. 32, pp. 48-77, 2002.
15. P. Auer, "Using confidence bounds for exploitation-exploration tradeoffs," J. Machine Learning Res., vol. 3, pp. 397-422, 2002.
16. D. Helmbold, N. Littlestone, and P. Long, "Apple tasting," Inf. Comput., vol. 161, no. 2, pp. 85-139, 2000.
17. P. Auer, N. Cesa-Bianchi, Y. Freund, and R. Schapire, "The non-stochastic multiarmed bandit problem," SIAM J. Computing, vol. 32, no. 1, 2002.
18. W. Hoeffding, "Probability inequalities for sums of bounded random variables," J. Amer. Statist. Assoc., vol. 58, pp. 13-30, 1963.
19. Y. Chow and H. Teicher, Probability Theory. New York: Springer-Verlag, 1988.
20. D. Freedman, "On tail probabilities for martingales," Ann. Probab., vol. 3, pp. 100-118, 1975.
21. L. Birgé, "A New Look at an Old Result: Fano's Lemma," Université Paris 6, Paris, France, Tech. Rep., 2001.
22. P. Massart, Concentration Inequalities and Model Selection: Saint-Flour Summer School Lecture Notes, 2003, to be published.