Abstract
In this paper the sequential prediction problem with expert advice is considered when the loss is unbounded under partial monitoring scenarios. We deal with a wide class of the partial monitoring problems: the combination of the label efficient and multi-armed bandit problem, that is, where the algorithm is only informed about the performance of the chosen expert with probability ε≤1. For bounded losses an algorithm is given whose expected regret scales with the square root of the loss of the best expert. For unbounded losses we prove that Hannan consistency can be achieved, depending on the growth rate of the average squared losses of the experts.
We would like to thank Gilles Stoltz and András György for useful comments.
This research was supported in part by the Hungarian Inter-University Center for Telecommunications and Informatics (ETIK).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Auer, P., Cesa-Bianchi, N., Freund, Y., Schapire, R.E.: Gambling in a rigged casino: the adversial multi-armed bandit problem. In: Proceedings of the 36th Annual Symposium on Foundations of Computer Science, FOCS 1995, Washington, DC, USA, October 1995, pp. 322–331. IEEE Computer Society Press, Los Alamitos, CA (1995)
Blackwell, D.: An analog of the minimax theorem for vector payoffs. Pacific Journal of Mathematics 6, 1–8 (1956)
Cesa-Bianchi, N., Freund, Y., Helmbold, D.P., Haussler, D., Schapire, R., Warmuth, M.K.: How to use expert advice. Journal of the ACM 44(3), 427–485 (1997)
Cesa-Bianchi, N., Lugosi, G.: Prediction, Learning, and Games. Cambridge University Press, Cambridge (2006)
Cesa-Bianchi, N., Lugosi, G., Stoltz, G.: Minimizing regret with label efficient prediction. IEEE Trans. Inform. Theory 51, 2152–2162 (2005)
Cesa-Bianchi, N., Mansour, Y., Stoltz, G.: Improved second-order bounds for prediction with expert advice. In: Auer, P., Meir, R. (eds.) COLT 2005. LNCS, vol. 3559, pp. 217–232. Springer, Heidelberg (2005)
Cesa-Bianchi, N., Mansour, Y., Stoltz, G.: Improved second-order bounds for prediction with expert advice (submitted, 2006)
Chow, Y.S.: Local convergence of martingales and the law of large numbers. Annals of Mathematical Statistics 36, 552–558 (1965)
Györfi, L., Lugosi, G.: Strategies for sequential prediction of stationary time series. In: Dror, M., L’Ecuyer, P., Szidarovszky, F. (eds.) Modelling Uncertainty: An Examination of its Theory, Methods and Applications, pp. 225–248. Kluwer Academic Publishers, Dordrecht (2001)
Györfi, L., Ottucsák, G.: Sequential prediction of unbounded stationary time series (submitted, 2006)
György, A., Ottucsák, G.: Adaptive routing using expert advice. The Computer Journal 49(2), 180–189 (2006)
Hannan, J.: Approximation to bayes risk in repeated plays. In: Dresher, M., Tucker, A., Wolfe, P. (eds.) Contributions to the Theory of Games, vol. 3, pp. 97–139. Princeton University Press, Princeton (1957)
Hart, S., Mas-Colell, A.: A simple adaptive procedure leading to correlated equilibrium. Econometria 68(5), 181–200 (2002)
Littlestone, N., Warmuth, M.K.: The weighted majority algorithm. Information and Computation 108, 212–261 (1994)
Poland, J., Hutter, M.: Defensive universal learning with experts. In: Jain, S., Simon, H.U., Tomita, E. (eds.) ALT 2005. LNCS, vol. 3734, pp. 356–370. Springer, Heidelberg (2005)
Vovk, V.: Aggregating strategies. In: Proceedings of the 3rd Annual Workshop on Computational Learning Theory, Rochester, NY, pp. 372–383. Morgan Kaufmann, San Francisco (1990)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Allenberg, C., Auer, P., Györfi, L., Ottucsák, G. (2006). Hannan Consistency in On-Line Learning in Case of Unbounded Losses Under Partial Monitoring . In: Balcázar, J.L., Long, P.M., Stephan, F. (eds) Algorithmic Learning Theory. ALT 2006. Lecture Notes in Computer Science(), vol 4264. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11894841_20
Download citation
DOI: https://doi.org/10.1007/11894841_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-46649-9
Online ISBN: 978-3-540-46650-5
eBook Packages: Computer ScienceComputer Science (R0)