Online Decentralized Frank-Wolfe: From theoretical bound to applications in smart-building - Archive ouverte HAL Access content directly
Conference Papers Year :

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

(1, 2, 3) , (4, 5, 6) , (2, 7) , (2, 8, 7) , (2, 7)
1
2
3
4
5
6
7
8

Abstract

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
Origin : Files produced by the author(s)

Dates and versions

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

Identifiers

  • HAL Id : hal-03710138 , version 1

Cite

Angan Mitra, Nguyen Kim Thang, Tuan-Anh Nguyen, Denis Trystram, Paul Youssef. Online Decentralized Frank-Wolfe: From theoretical bound to applications in smart-building. GloTS 2022 - Global IoT Conference, Jun 2022, Dublin, Ireland. pp.1-12. ⟨hal-03710138⟩
52 View
30 Download

Share

Gmail Facebook Twitter LinkedIn More