Hoppa direkt till innehållet
Huvudmenyn dold.

Joint Statistical Seminars - Ali Dadras

Tid Tisdag 18 april, 2023 kl. 13:00 - 14:00
Plats MIT.A.346

Title: Federated Frank-Wolfe Algorithm

Abstract: Federated learning (FL) has gained much attention in recent years for building privacy-preserving collaborative learning systems. However, FL algorithms for constrained machine learning problems are still very limited, particularly when the projection step is costly. To this end, we propose a Federated Frank-Wolfe Algorithm (FedFW). FedFW provably finds an ε-suboptimal solution of the constrained empirical risk-minimization problem after 𝒪(ε-2) iterations if the objective function is convex. The rate becomes 𝒪(ε-3) if the objective is non-convex. The method enjoys data privacy, low per-iteration cost and communication of sparse signals. We demonstrate empirical performance of the FedFW algorithm on several machine learning tasks.

This is a joint work with Karthik Prakhya and Alp Yurtsever (Umeå University).

Evenemangstyp: Seminarium
Ali Dadras
Läs om Ali Dadras
Alp Yurtsever
Läs om Alp Yurtsever