AI RESEARCH
Sharp Gaussian approximations for Decentralized Federated Learning
arXiv CS.LG
•
ArXi:2505.08125v4 Announce Type: replace-cross Federated Learning has gained traction in privacy-sensitive collaborative environments, with local SGD emerging as a key optimization method in decentralized settings. While its convergence properties are well-studied, asymptotic statistical guarantees beyond convergence remain limited. In this paper, we present two generalized Gaussian approximation results for local SGD and explore their implications. First, we prove a Berry-Esseen theorem for the final local SGD iterates, enabling valid multiplier bootstrap procedures.