Andrew M. McDonald

activity

20142026

most citedNew Perspectives on k-Support and Cluster Norms

3 citations · 4 across the 5 of their papers we have counts for

collaborators

Showing cs.LGShow all

2 papers · 1 filter

cs.LG2016

Fitting Spectral Decay with the $k$ -Support Norm

Andrew M. McDonald, Massimiliano Pontil, Dimitris Stamos

The spectral $k$ -support norm enjoys good estimation properties in low rank matrix learning problems, empirically outperforming the trace norm. Its unit ball is the convex hull of…

cs.LG2015★ 1 cited

New Perspectives on $k$ -Support and Cluster Norms

Andrew M. McDonald, Massimiliano Pontil, Dimitris Stamos

We study a regularizer which is defined as a parameterized infimum of quadratics, and which we call the box-norm. We show that the k-support norm, a regularizer proposed by [Argyri…

Fitting Spectral Decay with the k-Support Norm

New Perspectives on k-Support and Cluster Norms

Fitting Spectral Decay with the $k$ -Support Norm

New Perspectives on $k$ -Support and Cluster Norms