Abstract
We study a high-dimensional generalized linear model and penalized empirical risk minimization with $\ell_1$ penalty. Our aim is to provide a non-trivial illustration that non-asymptotic bounds for the estimator can be obtained without relying on the chaining technique and/or the peeling device.
Information
Published: 1 January 2007
First available in Project Euclid: 4 December 2007
zbMATH: 1176.62071
MathSciNet: MR2459935
Digital Object Identifier: 10.1214/074921707000000319
Subjects:
Primary:
62G08
Keywords:
Convex hull
,
convex loss
,
covering number
,
non-asymptotic bound
,
penalized M-estimation
Rights: Copyright © 2007, Institute of Mathematical Statistics
