Optimal Kernel Selection in Kernel Fisher Discriminant Analysis

S.-J. Kim, A. Magnani, and S. Boyd

Proceedings of the 23rd International Conference on Machine Learning (ICML 2006), p465-472.

In Kernel Fisher discriminant analysis (KFDA), we carry out Fisher linear discriminant analysis in a high dimensional feature space defined implicitly by a kernel. The performance of KFDA depends on the choice of the kernel; in this paper, we consider the problem of finding the optimal kernel, over a given convex set of kernels. We show that this optimal kernel selection problem can be reformulated as a tractable convex optimization problem which interior-point methods can solve globally and efficiently. The kernel selection method is demonstrated with some UCI machine learning benchmark examples.