Abstract
We investigate label efficient prediction, a variant of the problem of prediction with expert advice, proposed by Helmbold and Panizza, in which the forecaster does not have access to the outcomes of the sequence to be predicted unless he asks for it, which he can do for a limited number of times. We determine matching upper and lower bounds for the best possible excess error when the number of allowed queries is a constant. We also prove that a query rate of order (ln n) (ln ln n)2/n is sufficient for achieving Hannan consistency, a fundamental property in game-theoretic prediction models. Finally, we apply the label efficient framework to pattern classification and prove a label efficient mistake bound for a randomized variant of Littlestone’s zero-threshold Winnow algorithm.
The authors gratefully acknowledge partial support by the PASCAL Network of Excellence under EC grant no. 506778.
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.: The nonstochastic multiarmed bandit problem. SIAM Journal on Computing 32(1), 48–77 (2002)
Auer, P., Cesa-Bianchi, N., Gentile, C.: Adaptive and self-confident on-line learning algorithms. Journal of Computer and System Sciences 64(1) (2002)
Birgé, L.: A new look at an old result: Fano’s lemma. Technical report, Université Paris 6 (2001)
Cesa-Bianchi, N., Freund, Y., Haussler, D., Helmbold, D.P., Schapire, R., Warmuth, M.K.: How to use expert advice. Journal of the ACM 44(3), 427–485 (1997)
Chow, Y.S., Teicher, H.: Probability Theory. Springer, Heidelberg (1988)
Cover, T.M., Thomas, J.A.: Elements of Information Theory. John Wiley and Sons, Chichester (1991)
Hannan, J.: Approximation to Bayes risk in repeated play. Contributions to the theory of games 3, 97–139 (1957)
Helmbold, D.P., Panizza, S.: Some label efficient learning results. In: Proceedings of the 10th Annual Conference on Computational Learning Theory, pp. 218–230. ACM Press, New York (1997)
Hoeffding, W.: Probability inequalities for sums of bounded random variables. Journal of the American Statistical Association 58, 13–30 (1963)
Littlestone, N.: Mistake Bounds and Logarithmic Linear-threshold Learning Algorithms. PhD thesis, University of California at Santa Cruz (1989)
Massart, P.: Concentration inequalities and model selection. Saint-Flour summer school lecture notes (2003) (to appear)
Piccolboni, A., Schindelhauer, C.: Discrete prediction games with arbitrary feedback and loss. In: Proceedings of the 14th Annual Conference on Computational Learning Theory, pp. 208–223 (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cesa-Bianchi, N., Lugosi, G., Stoltz, G. (2004). Minimizing Regret with Label Efficient Prediction. In: Shawe-Taylor, J., Singer, Y. (eds) Learning Theory. COLT 2004. Lecture Notes in Computer Science(), vol 3120. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-27819-1_6
Download citation
DOI: https://doi.org/10.1007/978-3-540-27819-1_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22282-8
Online ISBN: 978-3-540-27819-1
eBook Packages: Springer Book Archive