Penalised least square in sparse setting with convex penalty and non gaussian errors - Université Clermont Auvergne Accéder directement au contenu
Article Dans Une Revue Acta Mathematica Scientia Année : 2021

Penalised least square in sparse setting with convex penalty and non gaussian errors

Résumé

This paper considers the penalized least squares estimators with convex penalties or regularisation norms. We provide sparsity oracles inequalities for the prediction error for a general convex penalty and for the particular cases of Lasso and Group Lasso estimators in a regression setting. The main contributions are that our oracle inequalities are established for the more general case where the observations noise is issued from probability measures that satisfy a weak spectral gap (or Poincaré) inequality instead of gaussian distributions, and five easier to verify bounds on compatibility. We Illustrate our results on a heavy tailed example and a sub gaussian one; we especially give the explicit bounds of the oracle inequalities for these two special examples.
Fichier principal
Vignette du fichier
paper-dedicaceYU.pdf (376.83 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03240201 , version 1 (28-05-2021)

Licence

Paternité

Identifiants

Citer

Doualeh Abdillahi-Ali, Nourddine Azzaoui, Arnaud Guillin, Guillaume Le Mailloux, Tomoko Matsui. Penalised least square in sparse setting with convex penalty and non gaussian errors. Acta Mathematica Scientia, 2021, 41 (6), pp.2198-2216. ⟨10.1007/s10473-021-0624-0⟩. ⟨hal-03240201⟩
150 Consultations
68 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More