Abstract
We investigate the fat-shattering dimension and the localized Rademacher averages of kernel machines and their connection to the eigenvalues associated with the kernel.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
K. Ball: Volumes of sections on cubes and related problems, in Lecture Notes in Mathematics 1470, 36–47, Springer Berlin.
P. L. Bartlett, O. Bousquet, S. Mendelson: Localized Rademacher Averages, these proceedings.
F. Cucker, S. Smale: On the mathematical foundations of learning, preprint.
V. De la Peña, E. Giné: Decoupling: from dependence to independence, Springer, 1999.
P. Massart: About the constants in Talagrand’s concentration inequality for empirical processes, Annals of Probability, 28(2) 863–884, 2000.
S. Mendelson: Rademacher averages and phase transitions in Glivenko-Cantelli classes, IEEE transactions on Information Theory, Jan, 2002.
S. Mendelson: Improving the sample complexity using global data, to appear, IEEE transactions on Information Theory.
S. Mendelson, R. Vershynin: Entropy, Combinatorial Dimensions and Random Averages, these proceedings.
M. Meyer, A. Pajor: Sections of the unit ball of l p n, Journal of Functional Analysis 80(1), 109–123, 1988.
V. D. Milman, G. Schechtman: Asymptotic theory of finite dimensional normed spaces, Lecture Notes in Mathematics 1200, Springer 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.
A. W. Van der Vaart, J.A. Wellner: Weak convergence and Empirical Processes, Springer-Verlag, 1996.
R. C. Williamson, B. Scheolkopf, A. Smola: Generalization performance of regularization networks and support vector machines via entropy numbers of compact networks, IEEE transactions on Information Theory.
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
Mendelson, S. (2002). Geometric Parameters of Kernel Machines. 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_3
Download citation
DOI: https://doi.org/10.1007/3-540-45435-7_3
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