Minimax policies for combinatorial prediction games

Journal of Machine Learning Research

Volumn 19, Issue , 2011, Pages 107-132

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

^a ECOLE NORMALE SUPÉRIEURE   (France)

^b Princeton University   (United States)

^c UNIVERSITAT POMPEU FABRA   (Spain)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE;

BREGMAN PROJECTION; CONSTANT FACTORS; FULL INFORMATIONS; GRADIENT DESCENT; ONLINE LINEAR OPTIMIZATIONS; PARTIAL INFORMATION MODEL; UPPER AND LOWER BOUNDS; WEIGHTED AVERAGES;

SOFTWARE ENGINEERING;

EID: 84897474760     PISSN: 15324435     EISSN: 15337928     Source Type: Journal    
DOI: None     Document Type: Conference Paper

References (19)

1. J. Abernethy and A. Rakhlin. Beating the adaptive bandit with high probability. In 22nd annual conference on learning theory, 2009.
2. J. Abernethy, E. Hazan, and A. Rakhlin. Competing in the dark: An efficient algorithm for bandit linear optimization. In Rocco A. Servedio and Tong Zhang, editors, COLT, pages 263-274. Omnipress, 2008.
3. J.-Y. Audibert and S. Bubeck. Regret bounds and minimax policies under partial monitoring. JMLR, 11:2635-2686,2010.
4. B. Awerbuch and R.D. Kleinberg. Adaptive routing with end-to-end feedback: distributed learning and geometric approaches. In STOC '04: Proceedings of the thirty-sixth annual ACM symposium on Theory of computing, pages 45-53. ACM, 2004.
5. N. Cesa-Bianchi and G. Lugosi. Prediction, Learning, and Games. Cambridge University Press, 2006. ISBN 0521841089.
6. N. Cesa-Bianchi and G. Lugosi. Combinatorial bandits. In 22nd annual conference on learning theory, 2009.
7. N. Cesa-Bianchi and G. Lugosi. Combinatorial bandits. Submitted, 2010.
8. V. Dani, T. Hayes, and S.M. Kakade. The price of bandit information for online optimization. In Advances in Neural Information Processing Systems, volume 20, pages 345-352, 2008.
9. Y. Freund and R. E. Schapire. A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55:119-139, 1997. (Pubitemid 127433398)
10. A. György, T. Linder, G. Lugosi, and G. Ottucsák. The on-line shortest path problem under partial monitoring. J. Mach. Learn. Res., 8:2369-2403, 2007.
11. E. Hazan. A survey: The convex optimization approach to regret minimization. Working draft, 2010.
12. D. P. Helmbold and M. K. Warmuth. Learning permutations with exponential weights. JMLR, 10: 1705-1736, 2009.
13. M. Herbster and M. K. Warmuth. Tracking the best expert. Mach. Learn., 32:151-178, August 1998. ISSN 0885-6125.
14. A. Kalai and S. Vempala. Efficient algorithms for online decision problems. Journal of Computer and System Sciences, 71:291307, 2005.
15. S. Kale, L. Reyzin, and R. Schapire. Non-stochastic bandit slate problems. Advances in Neural Information Processing Systems, pages 1054-1062, 2010.
16. W. M. Kooien, M. K. Warmuth, and J. Kivinen. Hedging structured concepts. In 23rd annual conference on learning theory, 2010.
17. H. B. McMahan and A. Blum. Online geometric optimization in the bandit setting against an adaptive adversary. In In Proceedings of the 17th Annual Conference on Learning Theory, pages 109-123, 2004.
18. A. Rakhlin and A. Tewari. Lecture notes on online learning. 2008.
19. T. Uchiya, A. Nakamura, and M. Kudo. Algorithms for adversarial bandit problems with multiple plays. In Proc. of the 21st International Conference on Algorithmic Learning Theory, 2010.