This paper addresses the challenge of preserving privacy in Federated Learning (FL) within centralized systems, focusing on both trusted and untrusted server scenarios. We analyze this setting within the Stochastic Convex Optimization (SCO) framework, and devise methods that ensure Differential Privacy (DP) while maintaining optimal convergence rates for homogeneous and heterogeneous data distributions. Our approach, based on a recent stochastic optimization technique, offers linear computational complexity, comparable to non-private FL methods, and reduced gradient obfuscation. This work enhances the practicality of DP in FL, balancing privacy, efficiency, and robustness in a variety of server trust environment.

在集中式系统中的联邦学习（FL）中，本文解决了在受信任和不受信任服务器场景下保护隐私的挑战，分析了这种设置在随机凸优化（SCO）框架中，并设计了一种方法，以确保差分隐私（DP）同时保持同质和异质数据分布的最佳收敛速率。我们基于一种最近的随机优化技术的方法，提供了线性的计算复杂度，与非私有FL方法相当，并减少了梯度混淆。这项工作在各种服务器信任环境中平衡隐私、效率和稳健性，增强了DP在FL中的实用性。

私有和联邦随机凸优化: 集中系统的高效策略