Data sparse nonparametric regression with epsilon-insensitive losses - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Data sparse nonparametric regression with epsilon-insensitive losses

Résumé

Leveraging the celebrated support vector regression (SVR) method, we propose a unifying framework in order to deliver regression machines in reproducing kernel Hilbert spaces (RKHSs) with data sparsity. The central point is a new definition of epsilon-insensitivity, valid for many regression losses (including quantile and expectile regression) and their multivariate extensions. We show that the dual optimization problem to empirical risk minimization with epsilon-insensitivity involves a data sparse regularization. We also provide an analysis of the excess of risk as well as a randomized coordinate descent algorithm for solving the dual. Numerical experiments validate our approach.
Fichier principal
Vignette du fichier
acml2017.pdf (1.07 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01593459 , version 1 (02-08-2018)

Identifiants

  • HAL Id : hal-01593459 , version 1

Citer

Maxime Sangnier, Olivier Fercoq, Florence d'Alché-Buc. Data sparse nonparametric regression with epsilon-insensitive losses. 9th Asian Conference on Machine Learning (ACML 2017), Nov 2017, Séoul, South Korea. pp.192-207. ⟨hal-01593459⟩
422 Consultations
117 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More