A Unifying View of Multiple Kernel Learning

TL;DR

This paper introduces a unifying optimization framework for multiple kernel learning, encompassing existing methods, and provides theoretical and empirical analysis of its generalization capabilities.

Contribution

It presents a general optimization criterion that subsumes existing multiple kernel learning approaches and derives its dual form for efficient optimization.

Findings

Unified framework for multiple kernel learning

Theoretical generalization bounds via Rademacher complexity

Empirical validation through experiments

Abstract

Recent research on multiple kernel learning has lead to a number of approaches for combining kernels in regularized risk minimization. The proposed approaches include different formulations of objectives and varying regularization strategies. In this paper we present a unifying general optimization criterion for multiple kernel learning and show how existing formulations are subsumed as special cases. We also derive the criterion's dual representation, which is suitable for general smooth optimization algorithms. Finally, we evaluate multiple kernel learning in this framework analytically using a Rademacher complexity bound on the generalization error and empirically in a set of experiments.