Abstract
An algorithm is presented for online prediction that allows to track the best expert efficiently even if the number of experts is exponentially large, provided that the set of experts has a certain structure allowing efficient implementations of the exponentially weighted average predictor. As an example we work out the case where each expert is represented by a path in a directed graph and the loss of each expert is the sum of the weights over the edges in the path.
This research was supported in part by the Natural Sciences and Engineering Research Council (NSERC) of Canada, the NATO Science Fellowship of Canada, the János Bolyai Research Scholarship of the Hungarian Academy of Sciences, Spanish Ministry of Science and Technology and FEDER, grant BMF2003-03324, and by the PASCAL Network of Excellence under EC grant no. 506778.
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., Warmuth, M.K.: Tracking the best disjunction. Machine Learning 32(2), 127–150 (1998)
Blackwell, D.: An analog of the minimax theorem for vector payoffs. Pacific Journal of Mathematics 6, 1–8 (1956)
Bousquet, O., Warmuth, M.K.: Tracking a small set of experts by mixing past posteriors. Journal of Machine Learning Research 3, 363–396 (2002)
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)
Schapire, R.E., Helmbold, D.P.: Predicting nearly as well as the best pruning of a decision tree. Machine Learning 27, 51–68 (1997)
György, A., Linder, T., Lugosi, G.: Efficient algorithms and minimax bounds for zero-delay lossy source coding. IEEE Transactions on Signal Processing, 2337–2347 (August 2004)
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)
Herbster, M., Warmuth, M.K.: Tracking the best expert. Machine Learning, 1–29 (1998)
Herbster, M., Warmuth, M.K.: Tracking the best linear predictor. Journal of Machine Learning Research 1, 281–309 (2001)
Kalai, A., Vempala, S.: Efficient algorithms for online decision problems. In: Schölkopf, B., Warmuth, M.K. (eds.) COLT/Kernel 2003. LNCS (LNAI), vol. 2777, pp. 26–40. Springer, Heidelberg (2003)
Littlestone, N., Warmuth, M.K.: The weighted majority algorithm. Information and Computation 108, 212–261 (1994)
Pereira, F., Singer, Y.: An efficient extension to mixture techniques for prediction and decision trees. Machine Learning 36, 183–199 (1999)
Takimoto, E., Warmuth, M.: Predicting nearly as well as the best pruning of a planar decision graph. Theoretical Computer Science 288, 217–235 (2002)
Takimoto, E., Warmuth, M.K.: Path kernels and multiplicative updates. In: Kivinen, J., Sloan, R.H. (eds.) COLT 2002. LNCS (LNAI), vol. 2375, pp. 74–89. Springer, Heidelberg (2002)
Takimoto, E., Warmuth, M.K.: Path kernels and multiplicative updates. Journal of Machine Learning Research 4, 773–818 (2003)
Vovk, V.: Aggregating strategies. In: Proceedings of the Third Annual Workshop on Computational Learning Theory, New York. Association of Computing Machinery, pp. 372–383 (1990)
Vovk, V.: Derandomizing stochastic prediction strategies. Machine Learning 35(3), 247–282 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
György, A., Linder, T., Lugosi, G. (2005). Tracking the Best of Many Experts. In: Auer, P., Meir, R. (eds) Learning Theory. COLT 2005. Lecture Notes in Computer Science(), vol 3559. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11503415_14
Download citation
DOI: https://doi.org/10.1007/11503415_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26556-6
Online ISBN: 978-3-540-31892-7
eBook Packages: Computer ScienceComputer Science (R0)