Skip to Main content Skip to Navigation
Conference papers

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

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.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03710138
Contributor : Tuan-Anh NGUYEN HUU Connect in order to contact the contributor
Submitted on : Thursday, June 30, 2022 - 2:30:28 PM
Last modification on : Tuesday, July 26, 2022 - 9:56:35 AM

File

_GLOBAL_IOT_Decentralized_Fran...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03710138, version 1

Citation

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⟩

Share

Metrics

Record views

38

Files downloads

8