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}.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-00703714
Contributor : Marius Kwemou <>
Submitted on : Wednesday, May 20, 2015 - 4:14:53 PM
Last modification on : Thursday, January 11, 2018 - 6:12:20 AM
Long-term archiving on : Thursday, April 20, 2017 - 5:27:39 AM

Files

GL_Kwemou.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00703714, version 4
  • ARXIV : 1206.0710

Collections

Citation

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

Share

Metrics

Record views

232

Files downloads

162