Assumptionless consistency of the Lasso
Statistics Theory
2014-06-27 v5 Probability
Statistics Theory
Abstract
The Lasso is a popular statistical tool invented by Robert Tibshirani for linear regression when the number of covariates is greater than or comparable to the number of observations. The purpose of this note is to highlight the simple fact (noted in a number of earlier papers in various guises) that for the loss function considered in Tibshirani's original paper, the Lasso is consistent under almost no assumptions at all.
Keywords
Cite
@article{arxiv.1303.5817,
title = {Assumptionless consistency of the Lasso},
author = {Sourav Chatterjee},
journal= {arXiv preprint arXiv:1303.5817},
year = {2014}
}
Comments
10 pages. Typos corrected