THE BENEFIT OF GROUP SPARSITY

• 成果类型: Article
• 署名作者: Huang, Junzhou; Zhang, Tong
• 署名单位: Rutgers University System; Rutgers University New Brunswick; Rutgers University System; Rutgers University New Brunswick
• 刊物名称: ANNALS OF STATISTICS
• ISSN/ISSBN: 0090-5364
• DOI: 10.1214/09-AOS778
• 发表日期: 2010
• 页码: 1978-2004
• 关键词: group lasso; selection

摘要

This paper develops a theory for group Lasso using a concept called strong group sparsity. Our result shows that group Lasso is superior to standard Lasso for strongly group-sparse signals. This provides a convincing theoretical justification for using group sparse regularization when the underlying group structure is consistent with the data. Moreover, the theory predicts some limitations of the group Lasso formulation that are confirmed by simulation studies.