Unifying mirror descent and dual averaging - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue Mathematical Programming Année : 2023

Unifying mirror descent and dual averaging

Résumé

We introduce and analyze a new family of first-order optimization algorithms which generalizes and unifies both mirror descent and dual averaging. Within the framework of this family, we define new algorithms for constrained optimization that combines the advantages of mirror descent and dual averaging. Our preliminary simulation study shows that these new algorithms significantly outperform available methods in some situations.
Fichier principal
Vignette du fichier
1910.13742.pdf (527.06 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03921381 , version 1 (03-01-2023)

Identifiants

Citer

Anatoli Juditsky, Joon Kwon, Éric Moulines. Unifying mirror descent and dual averaging. Mathematical Programming, 2023, 199, pp.793-830. ⟨10.1007/s10107-022-01850-3⟩. ⟨hal-03921381⟩
164 Consultations
59 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More