Federated learning (FL) is a fast-developing technique that allows multiple workers to train a global model based on a distributed dataset. Conventional FL employs gradient descent algorithm, which may not be efficient enough. It is well known that Nesterov Accelerated Gradient (NAG) is more advantageous in centralized training environment, but it is not clear how to quantify the benefits of NAG in FL so far. In this work, we focus on a version of FL based on NAG (FedNAG) and provide a detailed convergence analysis. The result is compared with conventional FL based on gradient descent. One interesting conclusion is that as long as the learning step size is sufficiently small, FedNAG outperforms FedAvg. Extensive experiments based on real-world datasets are conducted, verifying our conclusions and confirming the better convergence performance of FedNAG.

中文翻译：

---

使用 Nesterov 加速梯度动量方法的联邦学习

联邦学习 (FL) 是一种快速发展的技术，它允许多个工作人员基于分布式数据集训练全局模型。传统的 FL 采用梯度下降算法，可能不够高效。众所周知，Nesterov Accelerated Gradient (NAG) 在集中训练环境中更具优势，但目前尚不清楚如何量化 NAG 在 FL 中的好处。在这项工作中，我们专注于基于 NAG (FedNAG) 的 FL 版本并提供详细的收敛分析。结果与基于梯度下降的传统 FL 进行了比较。一个有趣的结论是，只要学习步长足够小，FedNAG 的表现就优于 FedAvg。进行了基于真实世界数据集的大量实验，