One gradient frank-wolfe for decentralized online convex and submodular optimization - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

One gradient frank-wolfe for decentralized online convex and submodular optimization

Résumé

Decentralized learning has been studied intensively in recent years motivated by its wide applications in the context of federated learning. The majority of previous research focuses on the offline setting in which the objective function is static. However, the offline setting becomes unrealistic in numerous machine learning applications that witness the change of massive data. In this paper, we propose decentralized online algorithm for convex and continuous DR-submodular optimization, two classes of functions that are present in a variety of machine learning problems. Our algorithms achieve performance guarantees comparable to those in the centralized offline setting. Moreover, on average, each participant performs only a single gradient computation per time step. Subsequently, we extend our algorithms to the bandit setting. Finally, we illustrate the competitive performance of our algorithms in real-world experiments.
Fichier principal
Vignette du fichier
_Arxiv_One_Gradient_FW.pdf (572.33 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03835713 , version 1 (01-11-2022)

Identifiants

Citer

Tuan-Anh Nguyen, Nguyen Kim Thang, Denis Trystram. One gradient frank-wolfe for decentralized online convex and submodular optimization. ACML 2022 - 14th Asian Conference in Machine Learning, Dec 2022, Hyderabad, India. pp.1-33. ⟨hal-03835713⟩
96 Consultations
22 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More