Sparse Prediction with the $k$-Support Norm
Machine Learning
2012-06-13 v2 Machine Learning
Abstract
We derive a novel norm that corresponds to the tightest convex relaxation of sparsity combined with an penalty. We show that this new {\em -support norm} provides a tighter relaxation than the elastic net and is thus a good replacement for the Lasso or the elastic net in sparse prediction problems. Through the study of the -support norm, we also bound the looseness of the elastic net, thus shedding new light on it and providing justification for its use.
Cite
@article{arxiv.1204.5043,
title = {Sparse Prediction with the $k$-Support Norm},
author = {Andreas Argyriou and Rina Foygel and Nathan Srebro},
journal= {arXiv preprint arXiv:1204.5043},
year = {2012}
}