Translator Disclaimer
August 2010 The benefit of group sparsity
Junzhou Huang, Tong Zhang
Ann. Statist. 38(4): 1978-2004 (August 2010). DOI: 10.1214/09-AOS778

Abstract

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.

Citation

Download Citation

Junzhou Huang. Tong Zhang. "The benefit of group sparsity." Ann. Statist. 38 (4) 1978 - 2004, August 2010. https://doi.org/10.1214/09-AOS778

Information

Published: August 2010
First available in Project Euclid: 11 July 2010

zbMATH: 1202.62052
MathSciNet: MR2676881
Digital Object Identifier: 10.1214/09-AOS778

Subjects:
Primary: 62G05
Secondary: 62J05

Rights: Copyright © 2010 Institute of Mathematical Statistics

JOURNAL ARTICLE
27 PAGES


SHARE
Vol.38 • No. 4 • August 2010
Back to Top