Abstract
The generalization properties of learning classifiers with a polynomial kernel function are examined here. We first show that the generalization error of the learning machine depends on the properties of the separating curve, that is, the intersection of the input surface and the true separating hyperplane in the feature space. When the input space is one-dimensional, the problem is decomposed to as many one-dimensional problems as the number of the intersecting points. Otherwise, the generalization error is determined by the class of the separating curve. Next, we consider how the class of the separating curve depends on the true separating function. The class is maximum when the true separating polynomial function is irreducible and smaller otherwise. In either case, the class depends only on the true function and does not on the dimension of the feature space. The results imply that the generalization error does not increase even when the dimension of the feature space gets larger and that the so-called overmodeling does not occur in the kernel learning.
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
Aizerman, M.A., Braverman, E.M., Rozonoer, L.I.: Theoretical foundations of the potential function method in pattern recognition learning. Automation and Remote Control, 25 (1964) 821–837
Amari, S.: A universal theorem on learning curves. Neural Networks, 6 (1993) 161–166
Amari, S., Fujita, N., Shinomoto, S.: Four Types of Learning Curves. Neural Computation, 4 (1992) 605–618
Amari, S., Murata, N.: Statistical Theory of Learning Curves under Entropic Loss Criterion. Neural Computation, 5 (1993) 140–153
Baum, E.B., Haussler, D.: What Size Net Gives Valid Generalization? Neural Computation, 1 (1989) 151–160
Cox, D.: Ideals, Varieties, and Algorithms. Springer-Verlag, New York, NY (1997)
Cristianini, N., Shawe-Taylor, J.: An Introduction to Support Vector Machines. Cambridge Univ. Press, Cambridge, UK (2000)
Dietrich, R., Opper, M., Sompolinsky, H.: Statistical Mechanics of Support Vector Networks. Physical Review Letters, 82 (1999) 2975–2978
Ikeda, K.: Geometry and Learning Curves of Kernel Methods with Polynomial Kernels. Trans. of IEICE, J86-D-II (2003) in press (in Japanese).
Ikeda, K., Amari, S.: Geometry of Admissible Parameter Region in Neural Learning. IEICE Trans. Fundamentals, E79-A (1996) 409–414
Murata, N., Yoshizawa, S., Amari, S.: Network Information Criterions — Determining the Number of Parameters for an Artifcial Neural Network Model. IEEE Trans. Neural Networks, 5 (1994) 865–872
Opper, M., Haussler, D.: Calculation of the Learning Curve of Bayes Optimal Classification on Algorithm for Learning a Perceptron with Noise. Proc. 4th Ann. Workshop Comp. Learning Theory (1991) 75–87
Schölkopf, B., Burges, C., Smola, A.J.: Advances in Kernel Methods: Support Vector Learning. Cambridge Univ. Press, Cambridge, UK (1998)
Smola, A.J. et al. (eds.): Advances in Large Margin Classifiers. MIT Press, Cambridge, MA (2000)
Ueno, K.: Introduction to Algebraic Geometry. Iwanami-Shoten, Tokyo (1995) (in Japanese)
Valiant, L.G.: A Theory of the Learnable. Communications of ACM, 27 (1984) 1134–1142
Vapnik, V.N.: Statistical Learning Theory. John Wiley and Sons, New York, NY (1998)
Vapnik, V.N., Chervonenkis, A.Y.: On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities. Theory of Probability and its Applications, 16 (1971) 264–280
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ikeda, K. (2003). Generalization Error Analysis for Polynomial Kernel Methods — Algebraic Geometrical Approach. In: Kaynak, O., Alpaydin, E., Oja, E., Xu, L. (eds) Artificial Neural Networks and Neural Information Processing — ICANN/ICONIP 2003. ICANN ICONIP 2003 2003. Lecture Notes in Computer Science, vol 2714. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44989-2_25
Download citation
DOI: https://doi.org/10.1007/3-540-44989-2_25
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40408-8
Online ISBN: 978-3-540-44989-8
eBook Packages: Springer Book Archive