FedDANE: A Federated Newton-Type Method

Understand

Federated learning aims to jointly learn statistical models over massively distributed remote devices.

• In this work, we propose FedDANE, an optimization method that we adapt from DANE, a method for classical distributed optimization, to handle the practical constraints of federated learning.
• We provide convergence guarantees for this method when learning over both convex and non-convex functions.
• Despite encouraging theoretical results, we find that the method has underwhelming performance empirically.