Convergence Analysis of Block Majorize-Minimize Subspace Approach - LARA - Libre accès aux rapports scientifiques et techniques
Rapport (Rapport De Recherche) Année : 2022

Convergence Analysis of Block Majorize-Minimize Subspace Approach

Emilie Chouzenoux
Jean-Baptiste Fest
  • Fonction : Auteur
  • PersonId : 1211087

Résumé

We consider the minimization of a differentiable Lipschitz gradient but non necessarily convex, function F defined on R N. We propose an accelerated gradient descent approach which combines three strategies, namely (i) a variable metric derived from the majorization-minimization principle ; (ii) a subspace strategy incorporating information from the past iterates ; (iii) a block alternating update. Under the assumption that F satisfies the Kurdyka-Łojasiewicz property, we give conditions under which the sequence generated by the resulting block majorize-minimize subspace algorithm converges to a critical point of the objective function, and we exhibit convergence rates for its iterates.
Fichier principal
Vignette du fichier
8711-1.pdf (397.83 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03920026 , version 1 (03-01-2023)
hal-03920026 , version 2 (25-01-2023)

Identifiants

  • HAL Id : hal-03920026 , version 1

Citer

Emilie Chouzenoux, Jean-Baptiste Fest. Convergence Analysis of Block Majorize-Minimize Subspace Approach. Inria Saclay - Île de France. 2022. ⟨hal-03920026v1⟩
119 Consultations
102 Téléchargements

Partager

More