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.
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).