Non-asymptotic Oracle Inequalities for the Lasso and Group Lasso in high dimensional logistic model - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year : 2012

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 eigenvalues assumption as introduced in \cite{BRT}.
Fichier principal
Vignette du fichier
GL_Kwemou.pdf (318.27 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and 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)

Identifiers

Cite

Marius Kwemou. Non-asymptotic Oracle Inequalities for the Lasso and Group Lasso in high dimensional logistic model. 2012. ⟨hal-00703714v4⟩
324 View
496 Download

Altmetric

Share

Gmail Facebook X LinkedIn More