English

Some sharp performance bounds for least squares regression with $L_1$ regularization

Statistics Theory 2009-08-21 v1 Statistics Theory

Abstract

We derive sharp performance bounds for least squares regression with L1L_1 regularization from parameter estimation accuracy and feature selection quality perspectives. The main result proved for L1L_1 regularization extends a similar result in [Ann. Statist. 35 (2007) 2313--2351] for the Dantzig selector. It gives an affirmative answer to an open question in [Ann. Statist. 35 (2007) 2358--2364]. Moreover, the result leads to an extended view of feature selection that allows less restrictive conditions than some recent work. Based on the theoretical insights, a novel two-stage L1L_1-regularization procedure with selective penalization is analyzed. It is shown that if the target parameter vector can be decomposed as the sum of a sparse parameter vector with large coefficients and another less sparse vector with relatively small coefficients, then the two-stage procedure can lead to improved performance.

Keywords

Cite

@article{arxiv.0908.2869,
  title  = {Some sharp performance bounds for least squares regression with $L_1$ regularization},
  author = {Tong Zhang},
  journal= {arXiv preprint arXiv:0908.2869},
  year   = {2009}
}

Comments

Published in at http://dx.doi.org/10.1214/08-AOS659 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

R2 v1 2026-06-21T13:37:15.208Z