Fast Convergence Rate of Multiple Kernel Learning with Elastic-net Regularization
Machine Learning
2011-07-14 v2
Abstract
We investigate the learning rate of multiple kernel leaning (MKL) with elastic-net regularization, which consists of an -regularizer for inducing the sparsity and an -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 -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.
Keywords
Cite
@article{arxiv.1103.0431,
title = {Fast Convergence Rate of Multiple Kernel Learning with Elastic-net Regularization},
author = {Taiji Suzuki and Ryota Tomioka and Masashi Sugiyama},
journal= {arXiv preprint arXiv:1103.0431},
year = {2011}
}
Comments
21 pages, 0 figure