Simultaneous analysis of Lasso and Dantzig selector
Statistics Theory
2010-11-10 v3 Statistics Theory
Abstract
We exhibit an approximate equivalence between the Lasso estimator and Dantzig selector. For both methods we derive parallel oracle inequalities for the prediction risk in the general nonparametric regression model, as well as bounds on the estimation loss for in the linear model when the number of variables can be much larger than the sample size.
Cite
@article{arxiv.0801.1095,
title = {Simultaneous analysis of Lasso and Dantzig selector},
author = {Peter J. Bickel and Ya'acov Ritov and Alexandre B. Tsybakov},
journal= {arXiv preprint arXiv:0801.1095},
year = {2010}
}
Comments
Noramlization factor corrected