Weakly decomposable regularization penalties and structured sparsity
Statistics Theory
2012-12-11 v2 Statistics Theory
Abstract
It has been shown in literature that the Lasso estimator, or l1-penalized least squares estimator, enjoys good oracle properties. This paper examines which special properties of the l1-penalty allow for sharp oracle results, and then extends the situation to general norm-based penalties that satisfy a weak decomposability condition.
Keywords
Cite
@article{arxiv.1204.4813,
title = {Weakly decomposable regularization penalties and structured sparsity},
author = {Sara van de Geer},
journal= {arXiv preprint arXiv:1204.4813},
year = {2012}
}
Comments
19 pages