Pré-Publication, Document De Travail Année : 2026

A block-coordinate descent framework for non-convex composite optimization. Application to sparse precision matrix estimation

Résumé

Block-coordinate descent (BCD) is the method of choice to solve numerous large scale optimization problems, however their theoretical study for non-convex optimization, has received less attention. In this paper, we present a new block-coordinate descent (BCD) framework to tackle non-convex composite optimization problems, ensuring decrease of the objective function and convergence to a solution. This framework is general enough to include variable metric proximal gradient updates, proximal Newton updates, and alternated minimization updates. This generality allows to encompass three versions of the most used solvers in the sparse precision matrix estimation problem, deemed Graphical Lasso: graphical ISTA, Primal GLasso, and QUIC. We demonstrate the value of this new framework on non-convex sparse precision matrix estimation problems, providing convergence guarantees and up to a $100$-fold reduction in the number of iterations required to reach state-of-the-art estimation quality.

Fichier principal
Vignette du fichier
ima-authoring-template.pdf (613.2 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05449031 , version 1 (28-01-2026)

Licence

Identifiants

Citer

Guillaume Lauga. A block-coordinate descent framework for non-convex composite optimization. Application to sparse precision matrix estimation. 2026. ⟨hal-05449031⟩
82 Consultations
66 Téléchargements

Altmetric

Partager

  • More