FedSSO: A Federated Server-Side Second-Order Optimization Algorithm
This work addresses efficiency challenges in federated learning for distributed systems, though it appears incremental as it builds on existing server-side optimization approaches.
The authors tackled the problem of slow convergence and high communication costs in federated learning by proposing FedSSO, a server-side second-order optimization algorithm that approximates Quasi-Newton methods without client data, resulting in faster convergence and elimination of additional communication for second-order updates.
In this work, we propose FedSSO, a server-side second-order optimization method for federated learning (FL). In contrast to previous works in this direction, we employ a server-side approximation for the Quasi-Newton method without requiring any training data from the clients. In this way, we not only shift the computation burden from clients to server, but also eliminate the additional communication for second-order updates between clients and server entirely. We provide theoretical guarantee for convergence of our novel method, and empirically demonstrate our fast convergence and communication savings in both convex and non-convex settings.