Error bounds for Kernel Fisher Linear Discriminant in Gaussian Hilbert space

[edit]

Robert Durrant, Ata Kaban ;
Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, PMLR 22:337-345, 2012.

Abstract

We give a non-trivial, non-asymptotic upper bound on the classification error of the popular Kernel Fisher Linear Discriminant classifier under the assumption that the kernel-induced space is a Gaussian Hilbert space.

Related Material