Easy multiple kernel learning
Fabio Aiolli, Michele Donini · 2014
Abstract. The goal of Multiple Kernel Learning (MKL) is to combine kernels derived from multiple sources in a data-driven way with the aim to enhance the accuracy of a kernel based machine. In this paper, we propose a time and space efficient MKL algorithm that can easily cope with hundreds of thousands of kernels and more. We compared our algorithm with other baselines plus three state-of-the-art MKL methods showing that our approach is often superior. 1