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.

翻译：我们提出了一种名为DualFL（对偶化联邦学习）的新型训练算法，用于解决联邦学习中的分布式优化问题。该方法基于联邦学习问题的一种特定对偶形式。在问题的光滑性和强凸性多种设定下，DualFL能够实现通信加速。此外，该算法从理论上保证了对非精确局部求解器的适用性，即使在非精确局部解的情况下仍能保持最优的通信复杂度。DualFL是首个在代价函数非光滑或非强凸时仍能实现通信加速的联邦学习算法。数值结果表明，DualFL的实际性能与最先进的联邦学习算法相当，且对超参数调优具有鲁棒性。