Hannan Consistency in On-Line Learning in Case of Unbounded Losses Under Partial Monitoring
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.
Unable to display preview. Download preview PDF.
- 1.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)Google Scholar
- 7.Cesa-Bianchi, N., Mansour, Y., Stoltz, G.: Improved second-order bounds for prediction with expert advice (submitted, 2006)Google Scholar
- 9.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)Google Scholar
- 10.Györfi, L., Ottucsák, G.: Sequential prediction of unbounded stationary time series (submitted, 2006)Google Scholar
- 12.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)Google Scholar
- 16.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)Google Scholar