Abstract
It is shown that bootstrap approximations of support vector machines (SVMs) based on a general convex and smooth loss function and on a general kernel are consistent. This result is useful for approximating the unknown finite sample distribution of SVMs by the bootstrap approach.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Boser, B., Guyon, I., Vapnik, V.: A training algorithm for optimal margin classifiers. In: Proceedings of the Fifth Annual Workshop on Computational Learning Theory, COLT’92, Pittsburgh, pp. 144–152. ACM, New York (1992)
Christmann, A., Salibían-Barrera, M., Aelst, S.V.: Qualitative robustness of bootstrap approximations for kernel based methods. In: Becker, C., Fried, R., Kuhnt, S. (eds.) Robustness and Complex Data Structures, chapter 16, pp. 263–278. Springer, Heidelberg (2013). (Preprint available on http://arxiv.org/abs/1111.1876)
Cucker, F., Zhou, D.: Learning Theory: An Approximation Theory Viewpoint. Cambridge University Press, Cambridge (2007)
Denkowski, Z., Migórski, S., Papageorgiou, N.: An Introduction to Nonlinear Analysis: Theory. Kluwer, Boston (2003)
Devroye, L.: Any discrimination rule can have an arbitrarily bad probability of error for finite sample size. IEEE Trans. Pattern Anal. Mach. Intell. 4, 154–157 (1982)
Devroye, L., Györfi, L., Lugosi, G.: A Probabilistic Theory of Pattern Recognition. Springer, New York (1996)
Efron, B.: Bootstrap methods: another look at the jackknife. Ann. Stat. 7, 1–26 (1979)
Hable, R.: Asymptotic normality of support vector machine variants and other regularized kernel methods. J. Multivar. Anal. 106, 92–117 (2012)
Poggio, T., Girosi, F.: Networks for approximation and learning. Proc. IEEE 78(9), 1481–1497 (1990)
Schölkopf, B., Smola, A.: Learning with Kernels. Support Vector Machines, Regularization, Optimization, and Beyond. MIT, Cambridge (2002)
Smale, S., Zhou, D.: Learning theory estimates via integral operators and their approximations. Constr. Approx. 26, 153–172 (2007)
Steinwart, I., Christmann, A.: Support Vector Machines. Springer, New York (2008)
van der Vaart, A., Wellner, J.: Weak Convergence and Empirical Processes. Springer, New York (1996)
Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995)
Vapnik, V.: Statistical Learning Theory. Wiley, New York (1998)
Vapnik, V., Lerner, A.: Pattern recognition using generalized portrait method. Autom. Remote Control 24, 774–780 (1963)
Wendland, H.: Scattered Data Approximation. Cambridge University Press, Cambridge (2005)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Christmann, A., Hable, R. (2013). On the Consistency of the Bootstrap Approach for Support Vector Machines and Related Kernel-Based Methods. In: Schölkopf, B., Luo, Z., Vovk, V. (eds) Empirical Inference. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41136-6_20
Download citation
DOI: https://doi.org/10.1007/978-3-642-41136-6_20
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41135-9
Online ISBN: 978-3-642-41136-6
eBook Packages: Computer ScienceComputer Science (R0)