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 :

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

Marius Kwemou
• Function : Author
• PersonId : 925848

#### 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}.

### 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

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

### Cite

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

### Export

BibTeX TEI Dublin Core DC Terms EndNote Datacite

322 View