Bandits with switching costs: T2/3 regret

Proceedings of the Annual ACM Symposium on Theory of Computing

Volumn , Issue , 2014, Pages 459-467

  Dekel, Ofer ^a   Ding, Jian ^b   Koren, Tomer ^c   Peres, Yuval ^a  

^a MICROSOFT RESEARCH   (United States)

^b UNIVERSITY OF CHICAGO   (United States)

^c TECHNION ISRAEL INSTITUTE OF TECHNOLOGY   (Israel)

Author keywords

Lower bounds; Multi armed Bandit; Online learning; Switching costs

Indexed keywords

COSTS; LEARNING ALGORITHMS; MARKOV PROCESSES; STATISTICS; TIME SWITCHES;

ADAPTIVE ADVERSARY; BANDIT FEEDBACKS; LOWER BOUNDS; MARKOV DECISION PROCESSES; MULTI ARMED BANDIT; MULTI-ARMED BANDIT PROBLEM; ONLINE LEARNING; SWITCHING COSTS;

E-LEARNING;

EID: 84904307224     PISSN: 07378017     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1145/2591796.2591868     Document Type: Conference Paper

References (17)

1. R. Arora, O. Dekel, and A. Tewari. Online bandit learning against an adaptive adversary: from regret to policy regret. In Proceedings of the Twenty-Ninth International Conference on Machine Learning, 2012.
2. J.-Y. Audibert, S. Bubeck, et al. Minimax policies for adversarial and stochastic bandits. In Proceedings of the 22th annual conference on learning theory (COLT), pages 217-226, 2009.
3. P. Auer, N. Cesa-Bianchi, Y. Freund, and R. Schapire. The nonstochastic multiarmed bandit problem. SIAM Journal on Computing, 32(1):48-77, 2002.
4. N. Cesa-Bianchi and G. Lugosi. Prediction, learning, and games. Cambridge University Press, 2006.
5. N. Cesa-Bianchi, Y. Freund, D. Haussler, D. P. Helmbold, R. E. Schapire, and M. K. Warmuth. How to use expert advice. Journal of the ACM, 44(3):427-485, May 1997.
6. N. Cesa-Bianchi, O. Dekel, and O. Shamir. Online learning with switching costs and other adaptive adversaries. In Advances in Neural Information Processing Systems 26, 2013.
7. F. R. K. Chung and P. D. Seymour. Graphs with small bandwidth and cutwidth. Discrete Mathematics, 75(1- 3):113-119, 1989.
8. T. Cover and J. Thomas. Elements of information theory. John Wiley & Sons, 2006.
9. O. Dekel and E. Hazan. Better rates for any adversarial deterministic MDP. In Proceedings of the Thirtieth International Conference on Machine Learning, 2013.
10. Y. Freund and R. Schapire. A decision-theoretic generalization of on-line learning and an application to boosting. Journal of computer and System Sciences, 55(1): 119-139, 1997.
11. S. Geulen, B. Vöcking, and M. Winkler. Regret minimization for online buffering problems using the weighted majority algorithm. In Proceedings of the 23rd International Conference on Learning Theory, pages 132-143, 2010.
12. A. Gyorgy and G. Neu. Near-optimal rates for limiteddelay universal lossy source coding. In Information Theory Proceedings (ISIT), 2011 IEEE International Symposium on, pages 2218-2222. IEEE, 2011.
13. A. Kalai and S. Vempala. Efficient algorithms for online decision problems. Journal of Computer and System Sciences, 71:291-307, 2005.
14. N. Littlestone and M.Warmuth. The weighted majority algorithm. Information and Computation, 108:212-261, 1994.
15. G. Neu, A. György, C. Szepesvári, and A. Antos. Online Markov decision processes under bandit feedback. In Advances in Neural Information Processing Systems 23, pages 1804-1812, 2010.
16. A. Yao. Probabilistic computations: Toward a unified measure of complexity. In Proceedings of the 18th IEEE Symposium on Foundations of Computer Science (FOCS), pages 222-227, 1977.
17. J. Y. Yu, S. Mannor, and N. Shimkin. Markov decision processes with arbitrary reward processes. Mathematics of Operations Research, 34(3):737-757, 2009.