Online Decentralized Frank-Wolfe: From theoretical bound to applications in smart-building - INRIA - Institut National de Recherche en Informatique et en Automatique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Online Decentralized Frank-Wolfe: From theoretical bound to applications in smart-building

Résumé

The design of decentralized learning algorithms is important in the fast-growing world in which data are distributed over participants with limited local computation resources and communication. In this direction, we propose an online algorithm minimizing non-convex loss functions aggregated from individual data/models distributed over a network. We provide the theoretical performance guarantee of our algorithm and demonstrate its utility on a real life smart building.
Fichier principal
Vignette du fichier
_GLOBAL_IOT_Decentralized_Frank_Wolfe_Non_convex.pdf (583.86 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03710138 , version 1 (30-06-2022)

Licence

Paternité

Identifiants

Citer

Angan Mitra, Kim Thang Nguyen, Tuan-Anh Nguyen, Denis Trystram, Paul Youssef. Online Decentralized Frank-Wolfe: From theoretical bound to applications in smart-building. Global IoT Conference (GloTS 2022), Jun 2022, Dublin, Ireland. pp.43--54, ⟨10.1007/978-3-031-20936-9_4⟩. ⟨hal-03710138⟩
142 Consultations
113 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More