Communication Dans Un Congrès Année : 2025

Box-constrained L0 Bregman relaxations

Résumé

Regularization using the L0 pseudo-norm is a common approach to promote sparsity, with widespread applications in machine learning and signal processing. However, solving such problems is known to be NP-hard. Recently, the L0 Bregman relaxation (B-rex) has been introduced as a continuous, non-convex approximation of the L0 pseudo-norm. Replacing the L0 term with B-rex leads to exact continuous relaxations that preserve the global optimum while simplifying the optimization landscape, making non-convex problems more tractable for algorithmic approaches. In this paper, we focus on box-constrained exact continuous Bregman relaxations of L0-regularized criteria with general data terms, including least-squares, logistic regression, and Kullback-Leibler fidelities. Experimental results on synthetic data, compared with Branch-and-Bound methods, demonstrate the effectiveness of the proposed relaxations.

Fichier principal
Vignette du fichier
Brex_box_constraints_hal.pdf (678.65 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05114194 , version 1 (16-06-2025)

Licence

Identifiants

  • HAL Id : hal-05114194 , version 1

Citer

Mhamed Essafri, Luca Calatroni, Emmanuel Soubies. Box-constrained L0 Bregman relaxations. European Signal Processing Conference (EUSIPCO), European Association for Signal Processing (EURASIP), Sep 2025, Palerme (Italie), Italy. ⟨hal-05114194⟩
3394 Consultations
233 Téléchargements

Partager

  • More