A Note on Improved Loss Bounds for Multiple Kernel Learning

Details A Note on Improved Loss Bounds for Multiple Kernel Learning A Note on Improved Loss Bounds for Multiple Kernel Learning

2011-06-30

arxiv.org/abs/1106.6258v1

Computer Science

Learning

Extended proof

Scientific paper

The paper \cite{hs-11} presented a bound on the generalisation error of classifiers learned through multiple kernel learning. The bound has (an improved) \emph{additive} dependence on the number of kernels (with the same logarithmic dependence on this number). However, parts of the proof were incorrectly presented in that paper. This note remedies this weakness by restating the problem and giving a detailed proof of the Rademacher complexity bound from \cite{hs-11}.

Affiliated with

Also associated with

No associations

Rating

A Note on Improved Loss Bounds for 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 A Note on Improved Loss Bounds for Multiple Kernel Learning, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A Note on Improved Loss Bounds for Multiple Kernel Learning will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-35396