Machine Learning Researcher
2016-09 ECMLPKDD Riva di Garda, Italy Author(s): John Moeller, Vivek Srikumar, Sarathkrishna Swaminathan, Suresh Venkatasubramanian, and Dustin Webb
Kernel learning is the problem of determining the best kernel (either from a dictionary of fixed kernels, or from a smooth space of kernel representations) for a given task. In this paper, we describe a new approach to kernel learning that establishes connections between the Fourier-analytic representation of kernels arising out of Bochner's theorem and a specific kind of feed-forward network using cosine activations. We analyze the complexity of this space of hypotheses and demonstrate empirically that our approach provides scalable kernel learning superior in quality to prior approaches.