The Benefit of Group Sparsity

Simple item page
dc.creatorHuang, Junzhou
dc.creatorZhang, Tong
dc.date2009-01-20
dc.date2009-03-17
dc.date.accessioned2026-07-07T12:52:37Z
dc.date.available2026-07-07T12:52:37Z
dc.descriptionThis 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.
dc.identifierhttps://arxiv.org/abs/0901.2962
dc.identifierhttp://arxiv.org/abs/0901.2962
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/223351
dc.subjectMachine Learning
dc.subjectStatistics Theory
dc.titleThe Benefit of Group Sparsity
dc.typetext

Files

Collections

arXiv