|
|||||
|
|
Weakly decomposable regularization penalties and structured sparsity |
|
| Authors: | Sara van de Geer |
| Institution: | Seminar für Statistik, ETH Zurich |
| Abstract: | It has been shown in literature that the Lasso estimator, or ?1‐penalized least squares estimator, enjoys good oracle properties. This paper examines which special properties of the ?1‐penalty allow for sharp oracle results, and then extends the situation to general norm‐based penalties that satisfy a weak decomposability condition. |
| Keywords: | lasso regularization sharp oracle inequality sparsity weakly decomposable norm |