Abstract
We consider the design of online master algorithms for combining the predictions from a set of experts where the absolute loss of the master is to be close to the absolute loss of the best expert. For the case when the master must produce binary predictions, the Binomial Weighting algorithm is known to be optimal when the number of experts is large. It has remained an open problem how to design master algorithms based on binomial weights when the predictions of the master are allowed to be real valued. In this paper we provide such an algorithm and call it the Binning algorithm because it maintains experts in an array of bins. We show that this algorithm is optimal in a relaxed setting in which we consider experts as continuous quantities. The algorithm is efficient and near-optimal in the standard experts setting.
This is a preview of subscription content, log in via an institution to check access.
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 adversarial multi-armed bandit problem. In: Proceedings of the 36th Annual Symposium on Foundations of Computer Science, pp. 322–331. IEEE Computer Society Press, Los Alamitos (1995)
Cesa-Bianchi, N., Freund, Y., Haussler, D., Helmbold, D.P., Schapire, R.E., Warmuth, M.K.: How to use expert advice. Journal of the ACM 44(3), 427–485 (1997)
Cesa-Bianchi, N., Freund, Y., Helmbold, D.P., Warmuth, M.K.: On-line prediction and conversion strategies. Machine Learning 25, 71–110 (1996)
Freund, Y., Opper, M.: Drifting games and Brownian motion. Journal of Computer and System Sciences 64, 113–132 (2002)
Freund, Y.: Boosting a weak learning algorithm by majority. Information and Computation 121(2), 256–285 (1995)
Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences 55(1), 119–139 (1997)
Haussler, D., Kivinen, J., Warmuth, M.K.: Sequential prediction of individual sequences under general loss functions. IEEE Transactions on Information Theory 44(2), 1906–1925 (1998)
Herbster, M., Warmuth, M.K.: Tracking the best expert. Journal of Machine Learning 32(2), 151–178 (1998)
Kivinen, J., Warmuth, M.K.: Additive versus exponentiated gradient updates for linear prediction. Information and Computation 132(1), 1–64 (1997)
Kivinen, J., Warmuth, M.K.: Averaging expert predictions. In: Fischer, P., Simon, H.U. (eds.) EuroCOLT 1999. LNCS, vol. 1572, pp. 153–167. Springer, Heidelberg (1999)
Littlestone, N., Warmuth, M.K.: The weighted majority algorithm. Information and Computation 108(2), 212–261 (1994); An early version appeared in FOCS 1989
Vovk, V.: Aggregating strategies. In: Proc. 3rd Annu. Workshop on Comput. Learning Theory, pp. 371–383. 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
Abernethy, J., Langford, J., Warmuth, M.K. (2006). Continuous Experts and the Binning Algorithm. In: Lugosi, G., Simon, H.U. (eds) Learning Theory. COLT 2006. Lecture Notes in Computer Science(), vol 4005. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11776420_40
Download citation
DOI: https://doi.org/10.1007/11776420_40
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-35294-5
Online ISBN: 978-3-540-35296-9
eBook Packages: Computer ScienceComputer Science (R0)