Kolar, Mladen; Lafferty, John; Wasserman, Larry Union support recovery in multi-task learning. (English) Zbl 1280.62047 J. Mach. Learn. Res. 12, 2415-2435 (2011). Summary: 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. Cited in 4 Documents MSC: 62G08 Nonparametric regression and quantile regression 62J07 Ridge regression; shrinkage estimators (Lasso) 68T05 Learning and adaptive systems in artificial intelligence Keywords:high-dimensional inference; multi-task learning; sparsity; normal means; minimax estimation PDFBibTeX XMLCite \textit{M. Kolar} et al., J. Mach. Learn. Res. 12, 2415--2435 (2011; Zbl 1280.62047) Full Text: arXiv Link