Fast Convergence Rate of Multiple Kernel Learning with Elastic-net Regularization

Details Fast Convergence Rate of Multiple Kernel Learning with Elastic-net Regularization Fast Convergence Rate of Multiple Kernel Learning with Elastic-net Regularization

2011-03-02

arxiv.org/abs/1103.0431v2

Statistics

Machine Learning

21 pages, 0 figure

Scientific paper

We investigate the learning rate of multiple kernel leaning (MKL) with elastic-net regularization, which consists of an $\ell_1$-regularizer for inducing the sparsity and an $\ell_2$-regularizer for controlling the smoothness. We focus on a sparse setting where the total number of kernels is large but the number of non-zero components of the ground truth is relatively small, and prove that elastic-net MKL achieves the minimax learning rate on the $\ell_2$-mixed-norm ball. Our bound is sharper than the convergence rates ever shown, and has a property that the smoother the truth is, the faster the convergence rate is.

Affiliated with

Also associated with

No associations

Rating

Fast Convergence Rate of Multiple Kernel Learning with Elastic-net Regularization 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 Fast Convergence Rate of Multiple Kernel Learning with Elastic-net Regularization, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Fast Convergence Rate of Multiple Kernel Learning with Elastic-net Regularization will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-474676