Screening Data Points in Empirical Risk Minimization via Ellipsoidal Regions and Safe Loss Functions - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Screening Data Points in Empirical Risk Minimization via Ellipsoidal Regions and Safe Loss Functions

Résumé

We design simple screening tests to automatically discard data samples in empirical risk minimization without losing optimization guarantees. We derive loss functions that produce dual objectives with a sparse solution. We also show how to regularize convex losses to ensure such a dual sparsity-inducing property, and propose a general method to design screening tests for classification or regression based on ellipsoidal approximations of the optimal set. In addition to producing computational gains, our approach also allows us to compress a dataset into a subset of representative points.
Fichier principal
Vignette du fichier
main_aistats.pdf (869.18 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02395624 , version 1 (05-12-2019)
hal-02395624 , version 2 (12-06-2020)

Identifiants

  • HAL Id : hal-02395624 , version 2

Citer

Grégoire Mialon, Alexandre d'Aspremont, Julien Mairal. Screening Data Points in Empirical Risk Minimization via Ellipsoidal Regions and Safe Loss Functions. AISTATS 2020 - 23rd International Conference on Artificial Intelligence and Statistics, Aug 2020, Palermo / Virtual, Italy. pp.3610-3620. ⟨hal-02395624v2⟩
2651 Consultations
82 Téléchargements

Partager

Gmail Facebook X LinkedIn More