We propose a novel training algorithm called DualFL (Dualized Federated Learning), for solving a distributed optimization problem in federated learning. Our approach is based on a specific dual formulation of the federated learning problem. DualFL achieves communication acceleration under various settings on smoothness and strong convexity of the problem. Moreover, it theoretically guarantees the use of inexact local solvers, preserving its optimal communication complexity even with inexact local solutions. DualFL is the first federated learning algorithm that achieves communication acceleration, even when the cost function is either nonsmooth or non-strongly convex. Numerical results demonstrate that the practical performance of DualFL is comparable to those of state-of-the-art federated learning algorithms, and it is robust with respect to hyperparameter tuning.

本文提出了一种名为DualFL的新型训练算法，可以解决联邦学习中分布式优化问题，并实现了在不同条件下的通信加速，在使用不精确本地解算器时也保持其最佳的通信复杂度。此外，这是第一个即使在成本函数为非平滑或非强凸时也能实现通信加速的联邦学习算法。

DualFL: 基于对偶的联邦学习算法，在一般凸域中具有通信加速