Timezone: »

Sparse Prediction with the $k$-Support Norm
Andreas Argyriou · Rina Foygel · Nati Srebro

Thu Dec 06 02:00 PM -- 12:00 AM (PST) @ Harrah’s Special Events Center 2nd Floor #None
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 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. But through studying our new norm, we also bound the looseness of the elastic net, thus shedding new light on it and providing justification for its use.

Author Information

Andreas Argyriou (Ecole Centrale de Paris)
Rina Foygel (Stanford University)
Nati Srebro (TTI-Chicago)

More from the Same Authors