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.
@article{arxiv.1008.5211,
title = {Union Support Recovery in Multi-task Learning},
author = {Mladen Kolar and John Lafferty and Larry Wasserman},
journal= {arXiv preprint arXiv:1008.5211},
year = {2010}
}