The Local Rademacher Complexity of Lp-Norm Multiple Kernel Learning

Details The Local Rademacher Complexity of Lp-Norm Multiple Kernel Learning The Local Rademacher Complexity of Lp-Norm Multiple Kernel Learning

2011-03-03

arxiv.org/abs/1103.0790v1

Statistics

Machine Learning

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

The Local Rademacher Complexity of Lp-Norm Multiple Kernel Learning does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with The Local Rademacher Complexity of Lp-Norm Multiple Kernel Learning, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and The Local Rademacher Complexity of Lp-Norm Multiple Kernel Learning will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-320114