Consistency of the group Lasso and multiple kernel learning

We consider the least-square regression problem with regularization by a block 1-norm, that is, a sum of Euclidean norms over spaces of dimensions larger than one. This problem, referred to as the group Lasso, extends the usual regularization by the 1-norm where all spaces have dimension one, where it is commonly referred to as the Lasso. In this paper, we study the asymptotic group selection consistency of the group Lasso. We derive necessary and sufficient conditions for the consistency of group Lasso under practical assumptions, such as model misspecification. When the linear predictors and Euclidean norms are replaced by functions and reproducing kernel Hilbert norms, the problem is usually referred to as multiple kernel learning and is commonly used for learning from heterogeneous data sources and for non linear variable selection. Using tools from functional analysis, and in particular covariance operators, we extend the consistency results to this infinite dimensional case a...

• Type: Journal
• Year: 2007
• Where: CORR
• Authors: Francis Bach
• Keywords: CORR 2007, Education, Euclidean Norms, Group Lasso, Least-square Regression Problem