Abstract
We use geometric methods to investigate several fundamental problems in machine learning. We present a new bound on the L p coveringn umbers of Glivenko-Cantelli classes for \( 1 \leqslant p < \infty \) in terms of the fat-shatteringdimension of the class, which does not depend on the size of the sample. Usingthe new bound, we improve the known sample complexity estimates and bound the size of the Sufficient Statistics needed for Glivenko-Cantelli classes.
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
R.A. Adams: Sobolev Spaces, Pure and Applied Mathematics series 69, Academic Press 1975.
M. Anthony, P.L. Bartlett: Neural Network Learning: Theoretical Foundations, Cambridge University Press, 1999.
N. Alon, S. Ben-David, N. Cesa-Bianchi, D. Haussler: Scale sensitive dimensions, uniform convergence and learnability, J. of ACM 44(4), 615–631, 1997.
P.L. Bartlett, S.R. Kulkarni, S.E. Posner: Coveringn umbers for real valued function classes, IEEE transactions on information theory, 43(5), 1721–1724, 1997.
P.L. Bartlett, P. Long: More theorems about scale sensitive dimensions and learning, Proceedings of the 8th annual conference on Computation Learning Theory, 392–401, 1995.
R.M. Dudley: The sizes of compact subsets of Hilbert space and continuity of Gaussian processes, J. of Functional Analysis 1, 290–330, 1967.
R.M. Dudley, E. Giné, J. Zinn: Uniform and universal Glivenko-Cantelli classes, J. Theoret. Prob. 4, 485–510, 1991.
M. Ledoux, M. Talagrand: Probability in Banach spaces, Springer Verlag 1992.
J. Lindenstrauss, L. Tzafriri: Classical Banach Spaces Vol II, Springer Verlag.
S. Mendelson: Rademacher Averages and phase transitions in Glivenko-Cantelli classes, preprint.
S. Mendelson, N. Tishby: Statistical Sufficiency for Classes in Empirical L 2 Spaces, Proceedings of the 13th annual conference on Computational Learning Theory, 81–89, 2000.
A. Pajor: Sous espaces ln/1 des espaces de Banach, 1985
G. Pisier: Probabilistic methods in the geometry of Banach spaces, Probability and Analysis, Lecture notes in Mathematics 1206, 167–241, Springer Verlag 1986.
G. Pisier: The volume of convex bodies and Banach space geometry, Cambridge University Press, 1989.
M. Talagrand: Sharper bounds for Gaussian and empirical processes, Annals of Probability, 22(1), 28–76, 1994.
N. Tomczak-Jaegermann: Banach-Mazur distance and finite-dimensional operator Ideals, Pitman monographs and surveys in pure and applied Mathematics 38, 1989
V. Vapnik, A. Chervonenkis: Necessary and sufficient conditions for uniform convergence of means to mathematical expectations, Theory Prob. Applic. 26(3), 532–553, 1971
A.W. Van-der-Vaart, J.A. Wellner: Weak convergence and Empirical Processes, Springer-Verlag, 1996.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mendelson, S. (2001). Geometric Methods in the Analysis of Glivenko-Cantelli Classes. In: Helmbold, D., Williamson, B. (eds) Computational Learning Theory. COLT 2001. Lecture Notes in Computer Science(), vol 2111. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44581-1_17
Download citation
DOI: https://doi.org/10.1007/3-540-44581-1_17
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42343-0
Online ISBN: 978-3-540-44581-4
eBook Packages: Springer Book Archive