Unifying mirror descent and dual averaging - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Mathematical Programming Year : 2023

Unifying mirror descent and dual averaging

Abstract

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
Origin : Files produced by the author(s)

Dates and versions

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

Identifiers

Cite

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⟩
115 View
36 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More