We study the problem of corrupted sensing, a generalization of compresse...
We propose an approach to multivariate nonparametric regression that
gen...
We introduce a new family of matrix norms, the "local max" norms,
genera...
We derive a novel norm that corresponds to the tightest convex relaxatio...
We provide rigorous guarantees on learning with the weighted trace-norm ...
We consider the problem of approximately reconstructing a partially-obse...
The group lasso is a penalized regression method, used in regression pro...