Accelerated Variance Reduction Stochastic ADMM for Large-Scale Machine Learning.


Journal

IEEE transactions on pattern analysis and machine intelligence
ISSN: 1939-3539
Titre abrégé: IEEE Trans Pattern Anal Mach Intell
Pays: United States
ID NLM: 9885960

Informations de publication

Date de publication:
Dec 2021
Historique:
pubmed: 6 8 2020
medline: 6 8 2020
entrez: 6 8 2020
Statut: ppublish

Résumé

Recently, many stochastic variance reduced alternating direction methods of multipliers (ADMMs) (e.g., SAG-ADMM and SVRG-ADMM) have made exciting progress such as linear convergence rate for strongly convex (SC) problems. However, their best-known convergence rate for non-strongly convex (non-SC) problems is O(1/T) as opposed to O(1/T

Identifiants

pubmed: 32750780
doi: 10.1109/TPAMI.2020.3000512
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

4242-4255

Auteurs

Classifications MeSH