Volume 20, 2016
|Page(s)||309 - 331|
|Published online||05 August 2016|
Non-asymptotic oracle inequalities for the Lasso and Group Lasso in high dimensional logistic model
1 Laboratoire de Mathématique et modélisation d’Evry UMR CNRS 8071- USC INRA, Université d’Évry Val d’Essonne, Evry, France.
2 LERSTAD, Université Gaston Berger de Saint-Louis, Sénégal.
Received: 1 July 2014
Revised: 25 November 2015
Accepted: 4 December 2015
We consider the problem of estimating a function f0 in logistic regression model. We propose to estimate this function f0 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].
Mathematics Subject Classification: 62H12 / 62J12 / 62J07 / 62G20
Key words: Logistic model / Lasso / Group Lasso / high-dimensional / oracle inequality
© EDP Sciences, SMAI, 2016
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.