Can I read FedSSO: A Federated Server-Side Second-Order Optimization Algorithm on EtoBox?

FedSSO: A Federated Server-Side Second-Order Optimization Algorithm by Ma, Xin; Bao, Renyi; Jiang, Jinpeng; Liu, Yang; Jiang, Arthur; Yan, Jun; Liu, Xin; Pan, Zhisong is a scholarly article available to read on EtoBox.

What is FedSSO: A Federated Server-Side Second-Order Optimization Algorithm about?

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.

Author

Ma, Xin; Bao, Renyi; Jiang, Jinpeng; Liu, Yang; Jiang, Arthur; Yan, Jun; Liu, Xin; Pan, Zhisong

Published

2022

Language

EN