Non-asymptotic oracle inequalities for the Lasso and Group Lasso in high dimensional logistic model - Archive ouverte HAL Access content directly
Journal Articles ESAIM: Probability and Statistics Year : 2016

Non-asymptotic oracle inequalities for the Lasso and Group Lasso in high dimensional logistic model

Abstract

We consider the problem of estimating a function f(0) in logistic regression model. We propose to estimate this function f(0) by a sparse approximation build as a linear combination of elements of a given dictionary of p functions. This sparse approximation is selected by the Lasso or Group Lasso procedure. In this context, we state non asymptotic oracle inequalities for Lasso and Group Lasso under restricted eigenvalue assumption as introduced in [P.J. Bickel, Y. Ritov and A.B. Tsybakov, Ann. Statist. 37 (2009) 1705-1732].
Fichier principal
Vignette du fichier
Kwemou_2016_ESAIM Prob Stat_1.pdf (359.76 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Loading...

Dates and versions

hal-01601407 , version 1 (27-05-2020)

Licence

Copyright

Identifiers

Cite

Marius Kwemou. Non-asymptotic oracle inequalities for the Lasso and Group Lasso in high dimensional logistic model. ESAIM: Probability and Statistics, 2016, 20, pp.309-331. ⟨10.1051/ps/2015020⟩. ⟨hal-01601407⟩
60 View
31 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More