# 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 L_2 penalty. We show that this new k-support norm provides a tighter relaxation than the elastic net and can thus be advantageous in sparse prediction problems. We also bound the looseness of the elastic net, thus shedding new light on it and providing justification for its use.
Document type :
Conference papers
Domain :

https://hal.archives-ouvertes.fr/hal-00858954
Contributor : Paragios Nikos <>
Submitted on : Friday, September 6, 2013 - 11:52:30 AM
Last modification on : Tuesday, February 5, 2019 - 1:52:14 PM

### Identifiers

• HAL Id : hal-00858954, version 1

### Citation

Andreas Argyriou, Rina Foygel, Nathan Srebro. Sparse Prediction with the $k$-Support Norm. Neural Information Processing Systems, Dec 2012, Lake Tahoe, United States. pp.1466-1474. ⟨hal-00858954⟩

Record views