Pré-Publication, Document De Travail Année : 2023

Asymptotic convergence of iterative optimization algorithms

Résumé

This paper introduces a general framework for iterative optimization algorithms and establishes under general assumptions that their convergence is asymptotically geometric. We also prove that under appropriate assumptions, the rate of convergence can be lower bounded. The convergence is then only geometric, and we provide the exact asymptotic convergence rate. This framework allows to deal with constrained optimization and encompasses the Expectation Maximization algorithm and the mirror descent algorithm, as well as some variants such as the alpha-Expectation Maximization or the Mirror Prox algorithm. Furthermore, we establish sufficient conditions for the convergence of the Mirror Prox algorithm, under which the method converges systematically to the unique minimizer of a convex function on a convex compact set.

Fichier principal
Vignette du fichier
cdlc.pdf (438.45 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04000741 , version 1 (23-02-2023)

Licence

Identifiants

Citer

Randal Douc, Sylvain Le Corff. Asymptotic convergence of iterative optimization algorithms. 2023. ⟨hal-04000741⟩
141 Consultations
383 Téléchargements

Altmetric

Partager

  • More