Abstract
We investigate the generalization behavior of sequential prediction (online) algorithms, when data are generated from a probability distribution. Using some newly developed probability inequalities, we are able to bound the total generalization performance of a learning algorithm in terms of its observed total loss. Consequences of this analysis will be illustrated with examples.
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
Azuma, K.: Weighted sums of certain dependent random variables. Tohoku Math. Journal 3, 357–367 (1967)
Bennett, G.: Probability inequalities for the sum of independent random variables. Journal of the American Statistical Association 57, 33–45 (1962)
Blum, A., Kalai, A., Langford, J.: Beating the hold-out: Bounds for k-fold and progressive cross-validation. In: COLT 1999, pp. 203–208 (1999)
Cesa-Bianchi, N., Conconi, A., Gentile, C.: On the generalization ability of on-line learning algorithms. IEEE Transactions on Information Theory, 2050–2057 (2004)
Collins, M.: Discriminative training methods for hidden markov models: Theory and experiments with perceptron algorithms. In: Proc. EMNLP 2000 (2002)
de la Pẽna V.H.: A general class of exponential inequalities for martingales and ratios. The Annals of Probability 27, 537–564 (1999)
Freedman, D.A.: On tail probabilities for martingales. The Annals of Probability 3, 100–118 (1975)
Freund, Y., Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 55(1), 119–139 (1997)
Hoeffding, W.: Probability inequalities for sums of bounded random variables. Journal of the American Statistical Association 58(301), 13–30 (1963)
Littlestone, N.: From on-line to batch learning. In: COLT 1989, pp. 269–284 (1989)
Littlestone, N., Warmuth, M.K.: The weighted majority algorithm. Information and Computation 108, 212–261 (1994)
Vovk, V.: Aggregating strategies. In: COLT 1990, pp. 371–383 (1990)
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
Zhang, T. (2005). Data Dependent Concentration Bounds for Sequential Prediction Algorithms. 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_12
Download citation
DOI: https://doi.org/10.1007/11503415_12
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)