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

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

2009-08-20

arxiv.org/abs/0908.2869v1

Annals of Statistics 2009, Vol. 37, No. 5A, 2109-2144

Mathematics

Statistics Theory

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

Scientific paper

10.1214/08-AOS659

We derive sharp performance bounds for least squares regression with $L_1$ regularization from parameter estimation accuracy and feature selection quality perspectives. The main result proved for $L_1$ 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 $L_1$-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.

Affiliated with

Also associated with

No associations

Rating

Some sharp performance bounds for least squares regression with $L_1$ regularization does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Some sharp performance bounds for least squares regression with $L_1$ regularization, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Some sharp performance bounds for least squares regression with $L_1$ regularization will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-525991