Convergence Analysis of Block Majorize-Minimize Subspace Approach - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports (Research Report) Year : 2023

Convergence Analysis of Block Majorize-Minimize Subspace Approach

Emilie Chouzenoux
Jean-Baptiste Fest
  • Function : Author
  • PersonId : 1211087

Abstract

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
main (1).pdf (668.76 Ko) Télécharger le fichier

Dates and versions

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

Identifiers

  • HAL Id : hal-03920026 , version 2

Cite

Emilie Chouzenoux, Jean-Baptiste Fest. Convergence Analysis of Block Majorize-Minimize Subspace Approach. Inria Saclay - Île de France. 2023. ⟨hal-03920026v2⟩
97 View
68 Download

Share

Gmail Facebook X LinkedIn More