# Sparse Prediction with the $k$-Support Norm

Abstract : We derive a novel norm that corresponds to the tightest convex relaxation of sparsity combined with an $\ell_2$ penalty. We show that this new {\em $k$-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 $k$-support norm, we also bound the looseness of the elastic net, thus shedding new light on it and providing justification for its use.
Type de document :
Pré-publication, Document de travail
2012
Domaine :

https://hal.inria.fr/hal-00855999
Contributeur : Puneet Kumar Dokania <>
Soumis le : vendredi 30 août 2013 - 12:02:29
Dernière modification le : vendredi 12 janvier 2018 - 11:23:52

### Identifiants

• HAL Id : hal-00855999, version 1
• ARXIV : 1204.5043

### Citation

Andreas Argyriou, Rina Foygel, Nathan Srebro. Sparse Prediction with the $k$-Support Norm. 2012. 〈hal-00855999〉

### Métriques

Consultations de la notice