Abstract
The standard so-called experts algorithms are methods for utilizing a given set of “experts” to make good choices in a sequential decision-making problem. In the standard setting of experts algorithms, the decision maker chooses repeatedly in the same “state” based on information about how the different experts would have performed if chosen to be followed. In this paper we seek to extend this framework by introducing state information. More precisely, we extend the framework by allowing an experts algorithm to rely on state information, namely, partial information about the cost function, which is revealed to the decision maker before the latter chooses an action. This extension is very natural in prediction problems. For illustration, an experts algorithm, which is supposed to predict whether the next day will be rainy, can be extended to predicting the same given the current temperature.
We introduce new algorithms, which attain optimal performance in the new framework, and apply to more general settings than variants of regression that have been considered in the statistics literature.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Antos, A., Györfi, L., Kohler, M.: Lower bounds on the rate of convergence of nonparametric regression estimates. Journal of Statistical Planning and Inference 83(1), 91–100 (2000)
Arora, S., Hazan, E., Kale, S.: The multiplicative weights update method: a meta algorithm and applications. Manuscript (2005)
Blum, A., Kalai, A.: Universal portfolios with and without transaction costs. In: COLT ’97: Proceedings of the tenth annual conference on Computational learning theory, pp. 309–313. ACM Press, New York, USA (1997)
Cesa-Bianchi, N., Conconi, A., Gentile, C.: On the generalization ability of on-line learning algorithms. IEEE Transactions on Information Theory (2004)
Cesa-Bianchi, N., Freund, Y., Helmbold, D.P., Haussler, D., Schapire, R.E., Warmuth, M.K.: How to use expert advice. In: STOC ’93: Proceedings of the twenty-fifth annual ACM symposium on Theory of computing, pp. 382–391. ACM Press, New York, USA (1993)
Cesa-Bianchi, N., Lugosi, G.: Prediction, Learning, and Games. Cambridge University Press, New York, USA (2006)
Clarkson, K.L.: Nearest-neighbor searching and metric space dimensions. In: Shakhnarovich, G., Darrell, T., Indyk, P. (eds.) Nearest-Neighbor Methods for Learning and Vision: Theory and Practice, pp. 15–59. MIT Press, Cambridge (2006)
Cover, T.M., Ordentlich, E.: Universal portfolios with side information. 42, 348–363 (1996)
Cover, T.: Universal portfolios. Math. Finance 1, 1–19 (1991)
Flaxman, A., Kalai, A.T., McMahan, H.B.: Online convex optimization in the bandit setting: gradient descent without a gradient. In: Proceedings of 16th SODA, pp. 385–394 (2005)
Hazan, E., Kalai, A., Kale, S.: A.t Agarwal. Logarithmic regret algorithms for online convex optimization. In: COLT ’06: Proceedings of the 19’th annual conference on Computational learning theory (2006)
Krauthgamer, R., Lee, J.R.: Navigating nets: Simple algorithms for proximity search. In: 15th Annual ACM-SIAM Symposium on Discrete Algorithms, pp. 791–801 (January 2004)
Kivinen, J., Warmuth, M.K.: Averaging expert predictions. In: EuroCOLT ’99: Proceedings of the 4th European Conference on Computational Learning Theory, London, UK, pp. 153–167. Springer, Heidelberg (1999)
Littlestone, N., Warmuth, M.K.: The weighted majority algorithm. Information and Computation 108(2), 212–261 (1994)
Stone, C.J.: Optimal global rates of convergence for nonparametric regression. Annals of Statistics 10, 1040–1053 (1982)
Zinkevich, M.: Online convex programming and generalized infinitesimal gradient ascent. In: Proceedings of the Twentieth International Conference (ICML), pp. 928–936 (2003)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Hazan, E., Megiddo, N. (2007). Online Learning with Prior Knowledge. In: Bshouty, N.H., Gentile, C. (eds) Learning Theory. COLT 2007. Lecture Notes in Computer Science(), vol 4539. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-72927-3_36
Download citation
DOI: https://doi.org/10.1007/978-3-540-72927-3_36
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-72925-9
Online ISBN: 978-3-540-72927-3
eBook Packages: Computer ScienceComputer Science (R0)