Union Support Recovery in Multi-task Learning

Abstract

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.

References in corpus (4)

• On the conditions used to prove oracle results for the Lasso
• A note on the group lasso and a sparse group lasso
• Support union recovery in high-dimensional multivariate regression
• Oracle Inequalities and Optimal Inference under Group Sparsity

Cited by in corpus (7)

• A Survey on Multi-Task Learning
• Robust Inference on Average Treatment Effects with Possibly More Covariates than Observations
• Group Lasso with Overlaps: the Latent Group Lasso approach
• Multi-Stage Multi-Task Feature Learning
• Recovery of simultaneous low rank and two-way sparse coefficient matrices, a nonconvex approach
• Improved Support Recovery Guarantees for the Group Lasso With Applications to Structural Health Monitoring
• Sharp Threshold for Multivariate Multi-Response Linear Regression via Block Regularized Lasso