Learning with structured sparsity

This paper investigates a new learning formulation called structured sparsity, which is a naturalextensionofthestandardsparsityconceptinstatisticallearningandcompressivesensing. By allowing arbitrary structures on the feature set, this concept generalizes the group sparsity idea that has become popular in recent years. A general theory is developed for learning with structured sparsity, based on the notion of coding complexity associated with the structure. It is shown that if the coding complexity of the target signal is small, then one can achieve improved performance by using coding complexity regularization methods, which generalize the standard sparse regularization. Moreover, a structured greedy algorithm is proposed to eciently solve the structured sparsity problem. It is shown that the greedy algorithm approximately solves the coding complexity optimization problem under appropriate conditions. Experiments are included to demonstrate the advantage of structured sparsity over s...

• Type: Conference
• Year: 2009
• Where: ICML
• Authors: Junzhou Huang, Tong Zhang, Dimitris N. Metaxas
• Keywords: Group Sparsity Idea, ICML 2009, Machine Learning, Standard Sparsity, Structured Sparsity Problem