Learning kernels using local rademacher complexity
Venue
Advances in Neural Information Processing Systems (NIPS 2013), MIT Press.
Publication Year
2013
Authors
Corinna Cortes, Marius Kloft, Mehryar Mohri
BibTeX
Abstract
We use the notion of local Rademacher complexity to design new algorithms for
learning kernels. Our algorithms thereby benefit from the sharper learning bounds
based on that notion which, under certain general conditions, guarantee a faster
convergence rate. We devise two new learning kernel algorithms: one based on a
convex optimization problem for which we give an efficient solution using existing
learning kernel techniques, and another one that can be formulated as a
DC-programming problem for which we describe a solution in detail. We also re- port
the results of experiments with both algorithms in both binary and multi-class
classification tasks.
