Skip navigation
Skip navigation

ℓ 1 -regularised linear regression: persistence and oracle inequalities

Bartlett, Peter; Mendelson, Shahar; Neeman, Joseph

Description

We study the predictive performance of ℓ1-regularized linear regression in a model-free setting, including the case where the number of covariates is substantially larger than the sample size. We introduce a new analysis method that avoids the boundedne

CollectionsANU Research Publications
Date published: 2012
Type: Journal article
URI: http://hdl.handle.net/1885/20427
Source: Probability Theory and Related Fields
DOI: 10.1007/s00440-011-0367-2

Download

File Description SizeFormat Image
01_Bartlett_ℓ_1_-regularised_linear_2012.pdf356.99 kBAdobe PDF    Request a copy
02_Bartlett_ℓ_1_-regularised_linear_2012.pdf341.52 kBAdobe PDF    Request a copy


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  12 November 2018/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator