Published April 10, 2022
| Version v1
Preprint
Open
Online Decentralized Frank-Wolfe: From theoretical bound to applications in smart-building
Authors/Creators
- 1. Qarnot Computing
- 2. Université d'Evry Val d'Essonne
- 3. Université Grenoble Alpes
Description
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.