We propose a novel differentially private algorithm for online federated learning that employs temporally correlated noise to improve the utility while ensuring the privacy of the continuously released models. To address challenges stemming from DP noise and local updates with streaming noniid data, we develop a perturbed iterate analysis to control the impact of the DP noise on the utility. Moreover, we demonstrate how the drift errors from local updates can be effectively managed under a quasi-strong convexity condition. Subject to an $(\epsilon, \delta)$-DP budget, we establish a dynamic regret bound over the entire time horizon that quantifies the impact of key parameters and the intensity of changes in dynamic environments. Numerical experiments validate the efficacy of the proposed algorithm.

翻译：我们提出了一种新颖的差分隐私在线联邦学习算法，该算法采用时序关联噪声来提升效用，同时确保持续发布模型的隐私性。为应对差分隐私噪声和流式非独立同分布数据本地更新带来的挑战，我们开发了一种扰动脉动分析技术以控制差分隐私噪声对效用的影响。此外，我们证明了在拟强凸条件下可有效管理本地更新带来的漂移误差。在$(\epsilon, \delta)$-差分隐私预算约束下，我们建立了覆盖整个时间跨度的动态遗憾界，该界限量化了关键参数以及动态环境中变化强度的影响。数值实验验证了所提算法的有效性。