Kernel/Feature Selection for Support Vector Machines Applied to Materials Design

Abstract Support Vector Machines are classifiers with architectures determined by kernel functions. In these proceedings we propose a method for selecting the best SVM kernel for a given classification problem. Our method searches for the best kernel by remapping the data via a kernel variant of the classical Gram-Schmidt orthonormalization procedure then using Fisher’s linear discriminant on the remapped data. By specializing to the Veronese kernel we can also perform feature selection with this method. We perform both feature and kernel selection on a materials design problem.