High-probability regret bounds for bandit online linear optimization

21st Annual Conference on Learning Theory, COLT 2008

Volumn , Issue , 2008, Pages 335-341

  Bartlett, Peter L ^a   Dani, Varsha ^b   Hayes, Thomas P ^c   Kakade, Sham M ^c   Rakhlin, Alexander ^a   Tewari, Ambuj ^c  

^a UNIVERSITY OF CALIFORNIA   (United States)

^b UNIVERSITY OF CHICAGO   (United States)

^c TOYOTA TECHNOLOGICAL INSTITUTE AT CHICAGO   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ADAPTIVE ADVERSARY; HIGH PROBABILITY; OBLIVIOUS ADVERSARIES; ONLINE LINEAR OPTIMIZATIONS; OPTIMISTIC ESTIMATES; REGRET BOUNDS;

ALGORITHMS; OPTIMIZATION;

PROBABILITY;

EID: 80555137396     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (15)

1. Jacob Abernethy, Elad Hazan, and Alexander Rakhlin. Competing in the dark: An efficient algorithm for bandit linear optimization. In Proceedings of the 21st Annual Conference on Learning Theory (COLT), 2008. to appear.
2. Peter Auer, Nicolò Cesa-Bianchi, Yoav Freund, and Robert E. Schapire. The nonstochastic multiarmed bandit problem. SIAM Journal on Computing, 32(1): 48-77, 2003.
3. Baruch Awerbuch, David Holmer, Herb Rubens, and Robert Kleinberg. Provably competitive adaptive routing. In Proceedings of the 31st IEEE INFOCOM, volume 1, pages 631-641, 2005.
4. Baruch Awerbuch and Robert Kleinberg. Adaptive routing with end-to-end feedback: Distributed learning and geometric approaches. In Proceedings of the 36th ACM Symposium on Theory of Computing (STOC), 2004.
5. Nicolò Cesa-Bianchi and Claudio Gentile. Improved risk tail bounds for on-line algorithms. IEEE Transactions on Information Theory, 54(1): 386-39, Jan 2008.
6. Nicolò Cesa-Bianchi and Gábor Lugosi. Prediction, Learning, and Games. Cambridge University Press, 2006.
7. Varsha Dani and Thomas P. Hayes. Robbing the bandit: Less regret in online geometric optimization against an adaptive adversary. In Proceedings of the 17th ACM-SIAM Symposium on Discrete Algorithms (SODA), 2006.
8. Varsha Dani, Thomas P. Hayes, and Sham M. Kakade. The price of bandit information for online optimization. In J. C. Platt, D. Koller, Y. Singer, and S. Roweis, editors, Advances in Neural Information Processing Systems 20 (NIPS 2007). MIT Press, 2008.
9. Varsha Dani, Thomas P. Hayes, and Sham M. Kakade. Stochastic linear optimization under bandit feedback. In Proceedings of the 21st Annual Conference on Learning Theory (COLT), 2008. to appear.
10. David A. Freedman. On tail probabilities for martingales. The Annals of Probability, 3(1): 100-118, Feb 1975.
11. András György, Tamás Linder, Gábor Lugosi, and György Ottucsák. The on-line shortest path problem under partial monitoring. Journal of Machine Learning Research, 8: 2369-2403, 2007.
12. Adam Kalai and Santosh Vempala. Efficient algorithms for online decision problems. Journal of Computer and System Sciences, 71(3): 291-307, 2005.
13. Robert Kleinberg. Online decision problems with large strategy sets. PhD thesis, MIT, 2005.
14. H. Brendan McMahan and Avrim Blum. Online geometric optimization in the bandit setting against an adaptive adversary. In Proceedings of the 17th Annual Conference on Learning Theory (COLT), 2004.
15. Eiji Takimoto and Manfred K. Warmuth. Path kernels and multiplicative updates. Journal of Machine Learning Research, 4: 773-818, 2003.