Structured sparsity-inducing norms through submodular functions

Sparse methods for supervised learning aim at finding good linear predictors from as few variables as possible, i.e., with small cardinality of their supports. This combinatorial selection problem is often turned into a convex optimization problem by replacing the cardinality function by its convex envelope (tightest convex lower bound), in this case the 1-norm. In this paper, we investigate more general set-functions than the cardinality, that may incorporate prior knowledge or structural constraints which are common in many applications: namely, we show that for nondecreasing submodular set-functions, the corresponding convex envelope can be obtained from its Lov

• Type: Journal
• Year: 2010
• Where: CORR
• Authors: Francis Bach
• Keywords: Cardinality, Convex Envelope, CORR 2010, Education, Supervised Learning