On the Complexity of Learning the Kernel Matrix

NIPS 2002: Proceedings of the 15th International Conference on Neural Information Processing Systems

Volumn , Issue , 2002, Pages 399-406

  Bousquet, Olivier ^a   Herrmann, Daniel J L ^a  

^a MAX PLANCK INSTITUTE FOR BIOLOGICAL CYBERNETICS   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

ERROR ANALYSIS; SUPPORT VECTOR MACHINES;

COMPLEXITY BOUNDS; FUNCTION CLASS; GENERALIZATION ERROR BOUNDS; KERNEL MATRICES; LEARNING THE KERNEL; OVERFITTING; RADEMACHER COMPLEXITY; SINGLE KERNEL; SPECTRA'S; SUPPORT VECTORS MACHINE;

EIGENVALUES AND EIGENFUNCTIONS;

EID: 84874094866     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. O. Chapelle, V. Vapnik, O. Bousquet, and S. Mukherjee. Choosing multiple parameters for support vector machines. Machine Learning, 46(1):131-159, 2002.
2. N. Cristianini, J. Kandola, A. Elisseeff, and J. Shawe-Taylor. On optimizing kernel alignment. Journal of Machine Learning Research, 2002. To appear.
3. L. Devroye and G. Lugosi. Combinatorial Methods in Density Estimation. Springer-Verlag, New York, 2000.
4. J. Kandola, J. Shawe-Taylor and N. Cristianini. Optimizing Kernel Alignment over Combinations of Kernels. In Int Conf Machine Learning, 2002. In press.
5. G. Lanckriet, N. Cristianini, P. Bartlett, L. El Ghaoui, and M.I. Jordan. Learning the kernel matrix with semidefinite programming. In Int Conf Machine Learning, 2002. In press.
6. M. Ledoux and M. Talagrand. Probability in Banach Spaces. Springer-Verlag, 1991.
7. O. Bousquet, and D. J. L. Herrmann. Towards Structered Kernel Maschines. Work in Progress.