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. In particular, through
empirical simulations on both synthetic and real-world datasets, FedDANE
consistently underperforms baselines of FedAvg and FedProx in realistic
federated settings. We identify low device participation and statistical device
heterogeneity as two underlying causes of this underwhelming performance, and
conclude by suggesting several directions of future work.

本文介绍了 FedDANE，一种从分布式优化的方法 DANE 基础上，为应对联邦学习的现实约束而提出的一种优化方法。作者提供了该方法应用于凸性和非凸性函数时的收敛性保证，并通过从合成和真实数据集上的实验模拟，将 FedDANE 与 FedAvg 和 FedProx 的表现进行了类比，发现其性能不如基线模型，作者归因于设备参与率低和设备之间的统计异质性，并提出了一些未来工作的方向。