Safe rules for the identification of zeros in the solution of the SLOPE problem - SCEE - Equipe Signal, Communication et Electronique Embarquée Accéder directement au contenu
Article Dans Une Revue SIAM Journal on Mathematics of Data Science Année : 2023

Safe rules for the identification of zeros in the solution of the SLOPE problem

Résumé

In this paper we propose a methodology to accelerate the resolution of the socalled "Sorted LOne Penalized Estimation" (SLOPE) problem. Our method leverages the concept of "safe screening", well-studied in the literature for group-separable sparsity-inducing norms, and aims at identifying the zeros in the solution of SLOPE. More specifically, we introduce a family of n! safe screening rules for this problem, where n is the dimension of the primal variable, and propose a tractable procedure to verify if one of these tests is passed. Our procedure has a complexity O(n log n+LT) where T ≤ n is a problem-dependent constant and L is the number of zeros identified by the tests. We assess the performance of our proposed method on a numerical benchmark and emphasize that it leads to significant computational savings in many setups.
Fichier principal
Vignette du fichier
main.pdf (790.4 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03400322 , version 1 (25-10-2021)
hal-03400322 , version 2 (15-04-2022)

Licence

Identifiants

Citer

Clément Elvira, Cédric Herzet. Safe rules for the identification of zeros in the solution of the SLOPE problem. SIAM Journal on Mathematics of Data Science, 2023, 5 (1), pp.147-173. ⟨10.1137/21M1457631⟩. ⟨hal-03400322v2⟩
173 Consultations
70 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More