On the complexity of learning the kernel matrix

Advances in Neural Information Processing Systems

Volumn , Issue , 2003, Pages

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

^a MAX PLANCK INSTITUTE FOR BIOLOGICAL CYBERNETICS   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; EIGENVALUES AND EIGENFUNCTIONS; ERROR ANALYSIS;

COMPLEXITY BOUNDS; FUNCTION CLASS; GENERALIZATION ERROR BOUNDS; LEARNING THE KERNEL; OPTIMIZATION PROBLEMS; OVERFITTING; RADEMACHER COMPLEXITY; SINGLE KERNEL;

OPTIMIZATION;

EID: 84899006163     PISSN: 10495258     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 Lnt 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 Lnt 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.