Abstract
This note mainly focuses on a theoretical analysis of support vector machines with beta-mixing input sequences. The explicit bounds are derived on the rate at which the empirical means converge to their true values when the underlying process is beta-mixing. The uniform convergence approach is used to estimate the convergence rates of the support vector machine algorithms with beta-mixing inputs.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Aronszajn, N.: Theory of Reproducing Kernels. Trans. Amer. Math. Soc. 68 (1950) 337–404
Boser, B.E., Guyon, I., Vapnik, V.: A Training Algorithm for Optimal Margin Classifiers. In: Proceedings of the Fifth Annual Workshop of Computational Learning Theory, Vol.5, Pittsburgh, ACM (1992) 144–152
Burges, C.J.C.: A Tutorial on Support Vector Machines for Pattern Recognition. Data Mining and Knowledge Discovery 2 (1998) 121–167
Chen, D.R., Wu, Q., Ying, Y.M., Zhou, D.X.: Support Vector Machine Soft Margin Classifiers: Error Analysis. J. of Machine Learning Research 5 (2004) 1143–1175
Cortes, C., Vapnik, V.: Support-vector Networks. Machine Learning 20 (1995) 273–297
Cristianini, N., Shawe-Taylor, J.: An Introduction to Support Vector Machines. Cambridge University Press (2000)
Cucker, F., Smale, S.: On the Mathematical Foundations of Learning. Bull. Amer. Math. Soc. 39 (2002) 1–49
Devroye, L., Györfi, L., Lugosi, G.: A Probabilistic Theory of Pattern Recognition. Springer-Verlag, Berlin Heidelberg New York (1996)
Fisher, R.A.: The Use of Multiple Measurements in Taxonomic Problems. Annals of Eugenics 7 (1936) 179–188
Karandikara, R.L., Vidyasagar, M.: Rates of Uniform Convergence of Empirical Means with Mixing Processes. Statistics & Probability Letters 58 (2002) 297–307
Lin, Y.: Support Vector Machines and the Bayes Rule in Classification. Data Mining and Knowledge Discovery 6, 259–275 (2002)
Nobel, A., Dembo, A.: A Note on Uniform Laws of Averages for Dependent Processes. Statistics & Probability Letters 17 (1993) 169–172
Rosenblatt, F.: Principles of Neurodynamics. Spartan Book, New York (1962)
Smola, A.J., Schölkopf, B.: A Tutorial on Support Vector Regression. Statistics and Computing 14 (2004) 199–222
Steinwart, I.: Support Vector Machines are Universally Consistent. J. Complexity 18 (2002) 768–791
Vapnik, V.: Estimation of Dependences Based on Empirical Data. Springer-Verlag, Berlin Heidelberg New York (1982)
Vapnik, V.: Statistical Learning Theory. John Wiley & Sons (1998)
Vidyasagar, M.: Learning and Generalization with Applications to Neural Networks. Springer-Verlak, Berlin Heidelberg New York (2003)
Wu, Q., Ying, Y.M., Zhou, D.X.: Learning Theory: From Regression to Classification. In: Jetter K., Buhmann M., Haussmann W., Schaback R., Stoeckler J. (eds.): Topics in Multivariate Approximation and Interpolation, Elsevier (2006) 101-133
Yu, B.: Rates of Convergence of Empirical Processes for Mixing Sequences. Ann. Probab. 22 (1994) 94–116
Zhang, T.: Statistical Behavior and Consistency of Classification Methods Based on Convex Risk Minimization. Ann. Statis. 32 (2004) 56–85
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Li, L., Wan, C. (2006). Support Vector Machines with Beta-Mixing Input Sequences. In: Wang, J., Yi, Z., Zurada, J.M., Lu, BL., Yin, H. (eds) Advances in Neural Networks - ISNN 2006. ISNN 2006. Lecture Notes in Computer Science, vol 3971. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11759966_136
Download citation
DOI: https://doi.org/10.1007/11759966_136
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-34439-1
Online ISBN: 978-3-540-34440-7
eBook Packages: Computer ScienceComputer Science (R0)