Abstract
We investigate the behaviour of global and local Rademacher averages. We present new error bounds which are based on the local averages and indicate how data-dependent local averages can be estimated without a priori knowledge of the class at hand.
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
P. L. Bartlett, S. Boucheron and G. Lugosi. Model selection and error estimation. Machine Learning, 48, 85–113, 2002.
P. L. Bartlett and S. Mendelson. Rademacher and Gaussian Complexities: Risk Bounds and Structural Results. Proceedings of the Fourteenth Annual Conference on Computational Learning Theory, pp. 224–240, 2001.
S. Boucheron, G. Lugosi and P. Massart. Concentration inequalities using the entropy method. Preprint, CNRS-Université Paris-Sud. 2002.
O. Bousquet. A Bennett concentration inequality and its application to empirical processes. C. R. Acad. Sci. Paris, Ser. I, 334, pp. 495–500, 2002.
V. I. Koltchinskii. Rademacher penalties and structural risk minimization. Technical report, University of New Mexico, 2000.
V. I. Koltchinskii and D. Panchenko. Rademacher processes and bounding the risk of function learning. In High Dimensional Probability II, Eds. E. Gine, D. Mason and J. Wellner, pp. 443–459, 2000.
W. S. Lee, P. L. Bartlett and R. C. Williamson. Efficient agnostic learning of neural networks with bounded fan-in. IEEE Transactions on Information Theory, 42(6), 2118–2132, 1996.
P. Massart. Some applications of concentration inequalities to statistics. Annales de la Faculté des Sciences de Toulouse, IX:245–303, 2000.
S. Mendelson. Improving the sample complexity using global data. IEEE Transactions on Information Theory, 2002.
S. Mendelson and R. C. Williamson Agnostic learning nonconvex classes of function. To appear in Proceedings of the Fifteenth Annual Conference on Computational Learning Theory, 2002.
E. Rio Une inegalité de Bennett pour les maxima de processus empiriques. Colloque en l’honneur de J. Bretagnolle, D. Dacunha-Castelle et I. Ibragimov, 2001.
A. W. van der Vaart and J. A. Wellner. Weak Convergence and Empirical Processes. Springer, 1996.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bartlett, P.L., Bousquet, O., Mendelson, S. (2002). Localized Rademacher Complexities. In: Kivinen, J., Sloan, R.H. (eds) Computational Learning Theory. COLT 2002. Lecture Notes in Computer Science(), vol 2375. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45435-7_4
Download citation
DOI: https://doi.org/10.1007/3-540-45435-7_4
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43836-6
Online ISBN: 978-3-540-45435-9
eBook Packages: Springer Book Archive