The Local Rademacher Complexity of Lp-Norm Multiple Kernel Learning

TLDR: In this article, the authors derived an upper bound on the local Rademacher complexity of multiple kernel learning, which yields a tighter excess risk bound than global approaches, and derived consequences regarding excess loss, namely fast convergence rates of the order O(n^{-\frac{\alpha}{1+\alpha}) where α is the minimum eigenvalue decay rate of individual kernels.

Abstract: We derive an upper bound on the local Rademacher complexity of $\ell_p$-norm multiple kernel learning, which yields a tighter excess risk bound than global approaches. Previous local approaches aimed at analyzed the case $p=1$ only while our analysis covers all cases $1\leq p\leq\infty$, 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 of the order $O(n^{-\frac{\alpha}{1+\alpha}})$, where $\alpha$ is the minimum eigenvalue decay rate of the individual kernels.