Paper ID: 2208.00522

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

Angan Mitra, Nguyen Kim Thang, Tuan-Anh Nguyen, Denis Trystram, Paul Youssef

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.

Submitted: Jul 31, 2022