%0 Journal Article
%T Union Support Recovery in Multi-task Learning
%A Mladen Kolar
%A John Lafferty
%A Larry Wasserman
%J Statistics
%D 2010
%I arXiv
%X We sharply characterize the performance of different penalization schemes for the problem of selecting the relevant variables in the multi-task setting. Previous work focuses on the regression problem where conditions on the design matrix complicate the analysis. A clearer and simpler picture emerges by studying the Normal means model. This model, often used in the field of statistics, is a simplified model that provides a laboratory for studying complex procedures.
%U http://arxiv.org/abs/1008.5211v1