The Local Rademacher Complexity of Lp-Norm Multiple Kernel Learning

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 $1\le p\le \infty$, 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.

References in corpus (4)

• 2004 IMS Medallion Lecture: Local Rademacher complexities and oracle inequalities in risk minimization
• L2 Regularization for Learning Kernels
• Sparsity in multiple kernel learning
• Minimax-optimal rates for sparse additive models over kernel classes via convex programming

Cited by in corpus (5)

• Localized Multiple Kernel Learning---A Convex Approach
• Framework for Multi-task Multiple Kernel Learning and Applications in Genome Analysis
• Bayes EMbedding (BEM): Refining Representation by Integrating Knowledge Graphs and Behavior-specific Networks
• Sparse Multiple Kernel Learning with Geometric Convergence Rate
• How many moments does MMD compare?