Belhal Karimi

FedSKETCH: Communication-Efficient and Private Federated Learning via Sketching

2020 · arXiv (Cornell University)

Communication complexity and privacy are the two key challenges in Federated Learning where the goal is to perform a distributed learning through a large volume of devices. In this work, we introduce FedSKETCH and FedSKETCHGATE …

Minimization by Incremental Stochastic Surrogate Optimization for Large Scale Nonconvex Problems

2022 · HAL (Le Centre pour la Communication Scientifique Directe)

International audience