Union Support Recovery in Multi-task Learning

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. [abs] [ pdf ][ bib ] &copy JMLR 2011. ( edit, beta )

Authors

• Mladen Kolar Booth School of Business, the University of Chicago
• John Lafferty
• Larry Wasserman

Keywords

No keywords are indexed for this paper.