Abstract
We consider the problem of dynamically apportioning resources among a set of options in a worst-case on-line framework. The model we study can be interpreted as a broad, abstract extension of the well-studied on-line prediction model to a general decision-theoretic setting. We show that the multiplicative weight-update rule of Littlestone and Warmuth [10] can be adapted to this mode yielding bounds that are slightly weaker in some cases, but applicable to a considerably more general class of learning problems. We show how the resulting learning algorithm can be applied to a variety of problems, including gambling, multiple-outcome prediction, repeated games and prediction of points in ℝn. We also show how the weight-update rule can be used to derive a new boosting algorithm which does not require prior knowledge about the performance of the weak learning algorithm.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Nicolò Cesa-Bianchi, Yoav Freund, David P. Helmbold, David Haussler, Robert E. Schapire, and Manfred K. Warmuth. How to use expert advice. In Proceedings of the Twenty-Fifth Annual ACM Symposium on the Theory of Computing, pages 382–391, May 1993.
Thomas H. Chung. Approximate methods for sequential decision making using expert advice. In Proceedings of the Seventh Annual ACM Conference on Computational Learning Theory, pages 183–189, 1994.
Thomas M. Cover. Universal portfolios. Mathematics of Finance, 1(1):1–29, January 1991.
Harris Drucker, Robert Schapire, and Patrice Simard. Boosting performance in neural networks. International Journal of Pattern Recognition and Artificial Intelligence, 7(4):705–719, 1993.
Yoav Freund. Data Filtering and Distribution Modeling Algorithms for Machine Learning. PhD thesis, University of California at Santa Cruz, 1993. Retrievable from: ftp.cse.ucsc.edu/pub/tr/ucsc-crl-93-37.ps.Z.
Yoav Freund. Boosting a weak learning algorithm by majority. Information and Computation, To appear.
James Hannan. Approximation to Bayes risk in repeated play. In M. Dresher, A. W. Tucker, and P. Wolfe, editors, Contributions to the Theory of Games, volume III, pages 97–139. Princeton University Press, 1957.
David Haussler, Jyrki Kivinen, and Manfred K. Warmuth. Tight worst-case loss bounds for predicting with expert advice. In Proceedings of the Second European Conference on Computational Learning Theory, 1995.
Jyrki Kivinen and Manfred K. Warmuth. Using experts for predicting continuous outcomes. In Computational Learning Theory: EuroCOLT'93, pages 109–120, 1994.
Nick Littlestone and Manfred K. Warmuth. The weighted majority algorithm. Information and Computation, 108:212–261, 1994.
Robert E. Schapire. The strength of weak learnability. Machine Learning, 5(2):197–227, 1990.
Volodimir G. Vovk. Aggregating strategies. In Proceedings of the Third Annual Workshop on Computational Learning Theory, pages 371–383, 1990.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Freund, Y., Schapire, R.E. (1995). A desicion-theoretic generalization of on-line learning and an application to boosting. In: Vitányi, P. (eds) Computational Learning Theory. EuroCOLT 1995. Lecture Notes in Computer Science, vol 904. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-59119-2_166
Download citation
DOI: https://doi.org/10.1007/3-540-59119-2_166
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-59119-1
Online ISBN: 978-3-540-49195-8
eBook Packages: Springer Book Archive