Regret bounds and minimax policies under partial monitoring

Journal of Machine Learning Research

Volumn 11, Issue , 2010, Pages 2785-2863

  Audibert, Jean Yves ^a,c   Bubeck, Sébastien ^b  

^a UNIVERSITÉ PARIS EST   (France)

^b INRIA   (France)

^c CNRS   (France)

Author keywords

Bandits (adversarial and stochastic); Label efficient; Minimax rate; Online learning; Prediction with limited feedback; Regret bound; Upper confidence bound (UCB) policy

Indexed keywords

BANDITS (ADVERSARIAL AND STOCHASTIC); LIMITED FEEDBACK; MINIMAX; ONLINE LEARNING; REGRET BOUND; UPPER CONFIDENCE BOUND;

E-LEARNING; OPTIMIZATION; STOCHASTIC SYSTEMS;

FORECASTING;

EID: 78649420293     PISSN: 15324435     EISSN: 15337928     Source Type: Journal    
DOI: None     Document Type: Article

References (16)

1. C. Allenberg, P. Auer, L. Györfi, and G. Ottucsák. Hannan consistency in on-line learning in case of unbounded losses under partial monitoring. In ALT, volume 4264 of Lecture Notes in Computer Science, pages 229-243. Springer, 2006.
2. J.-Y. Audibert, R. Munos, and Cs. Szepesvári. Exploration- exploitation trade-off using variance estimates in multi-armed bandits. Theoretical Computer Science, 410:1876-1902, 2009.
3. P. Auer. Using confidence bounds for exploitation-exploration trade-offs. Journal of Machine Learning Research, 3:397-422, 2002.
4. P. Auer, N. Cesa-Bianchi, Y. Freund, and R. Schapire. Gambling in a rigged casino: the adversarial multi-armed bandit problem. In Proceedings of the 36th Annual Symposium on Foundations of Computer Science, pages 322-331. IEEE Computer Society Press, 1995.
5. P. Auer, N. Cesa-Bianchi, and P. Fischer. Finite-time analysis of the multiarmed bandit problem. Machine Learning Journal, 47(2-3):235-256, 2002a.
6. P. Auer, N. Cesa-Bianchi, Y. Freund, and R. Schapire. The non-stochastic multi-armed bandit problem. SIAM Journal on Computing, 32(1):48-77, 2002b.
7. K. Azuma. Weighted sums of certain dependent random variables. Tohoku Mathematical Journal, 19:357-367, 1967.
8. N. Cesa-Bianchi. Analysis of two gradient-based algorithms for on-line regression. Journal of Computer and System Sciences, 59(3):392-411, 1999.
9. N. Cesa-Bianchi and G. Lugosi. Prediction, Learning, and Games. Cambridge University Press, 2006.
10. N. Cesa-Bianchi, Y. Freund, D. P. Helmbold, D. Haussler, R. E. Schapire, and M. K. Warmuth. How to use expert advice. Journal of the ACM, 44(3):427-485, 1997.
11. N. Cesa-Bianchi, G. Lugosi, and G. Stoltz. Minimizing regret with label efficient prediction. IEEE: Transactions on Information Theory, 51:2152-2162, 2005.
12. D. A. Freedman. On tail probabilities for martingales. The Annals of Probability, 3:100-118, 1975.
13. A. György and G. Ottucsák. Adaptive routing using expert advice. Computer Journal-Oxford, 49(2):180-189, 2006.
14. D. Helmbold and S. Panizza. Some label efficient learning results. In Proceedings of the 10th annual conference on Computational learning theory, pages 218-230. ACM New York, NY, USA, 1997.
15. W. Hoeffding. Probability inequalities for sums of bounded random variables. Journal of the American Statistical Association, 58:13-30, 1963.
16. H. Robbins. Some aspects of the sequential design of experiments. Bulletin of the American Mathematics Society, 58:527-535, 1952.