The Local Rademacher Complexity of Lp-Norm Multiple Kernel Learning
Marius Kloft and Gilles Blanchard
Advances in Neural Information Processing Systems
Neural Information Processing Systems
, Vancouver, British Columbia, Canada
We derive an upper bound on the local Rademacher complexity of p-norm multiple kernel learning, which yields a tighter excess risk bound than global approaches. Previous local approaches analyzed the case p = 1 only while our
analysis covers all cases, assuming the different feature mappings corresponding to the different kernels to be uncorrelated. We also show a lower bound that shows that the bound is tight, and derive consequences regarding excess loss, namely fast convergence rates.