Learning with Non-Positive Kernels
C.S. Ong, X. Mary, S. Canu and A. Smola
In: 21th International Conference on Machine Learning (ICML), 4-8 Jul 2004, Banff.

Abstract

In this paper we show that many kernel methods can be adapted to deal with indefinite kernels, that is, kernels which are not positive semidefinite. They do not satisfy Mercer’s condition and they induce associated functional spaces called Reproducing Kernel Kre˘ın Spaces (RKKS), a generalization of Reproducing Kernel Hilbert Spaces (RKHS).

PDF - Requires Adobe Acrobat Reader or other PDF viewer.

[Edit]