Non-asymptotic Oracle Inequalities for the Lasso and Group Lasso in high dimensional logistic model - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2012

Non-asymptotic Oracle Inequalities for the Lasso and Group Lasso in high dimensional logistic model

Résumé

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 eigenvalues assumption as introduced in \cite{BRT}. Those theoretical results are illustrated through a simulation study.
Fichier principal
Vignette du fichier
MK_oracle_v2.pdf (454.72 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-00703714 , version 1 (04-06-2012)
hal-00703714 , version 2 (03-10-2012)
hal-00703714 , version 3 (14-12-2012)
hal-00703714 , version 4 (20-05-2015)

Identifiants

Citer

Marius Kwemou. Non-asymptotic Oracle Inequalities for the Lasso and Group Lasso in high dimensional logistic model. 2012. ⟨hal-00703714v2⟩
334 Consultations
497 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More