On the equivalence of Kernel Fisher discriminant analysis and Kernel Quadratic Programming Feature Selection

Abstract

We reformulate the Quadratic Programming Feature Selection (QPFS) method in a Kernel space to obtain a vector which maximizes the quadratic objective function of QPFS. We demonstrate that the vector obtained by Kernel Quadratic Programming Feature Selection is equivalent to the Kernel Fisher vector and, therefore, a new interpretation of the Kernel Fisher discriminant analysis is given which provides some computational advantages for highly unbalanced datasets.