On the Convergence of Federated Learning Algorithms without Data Similarity

arXiv:2403.02347v1 Announce Type: new
Abstract: Data similarity assumptions have traditionally been relied upon to understand the convergence behaviors of federated learning methods. Unfortunately, this approach often demands fine-tuning step sizes based on the level of data similarity. When data similarity is low, these small step sizes result in an unacceptably slow convergence speed for federated methods. In this paper, we present a novel and unified framework for analyzing the convergence of federated learning algorithms without the need for data similarity …

abstract algorithms arxiv assumptions convergence cs.gt cs.lg data federated learning fine-tuning low small type