Adaptive Federated Learning with Auto-Tuned Clients

arXiv:2306.11201v3 Announce Type: replace
Abstract: Federated learning (FL) is a distributed machine learning framework where the global model of a central server is trained via multiple collaborative steps by participating clients without sharing their data. While being a flexible framework, where the distribution of local data, participation rate, and computing power of each client can greatly vary, such flexibility gives rise to many new challenges, especially in the hyperparameter tuning on the client side. We propose $\Delta$-SGD, a simple step …

abstract arxiv auto client collaborative computing computing power cs.dc cs.lg data distributed distribution federated learning framework global machine machine learning math.oc multiple power rate server type via while