Privacy-preserving Federated Primal-dual Learning for Non-convex and Non-smooth Problems with Model Sparsification

arXiv:2310.19558v2 Announce Type: replace
Abstract: Federated learning (FL) has been recognized as a rapidly growing research area, where the model is trained over massively distributed clients under the orchestration of a parameter server (PS) without sharing clients' data. This paper delves into a class of federated problems characterized by non-convex and non-smooth loss functions, that are prevalent in FL applications but challenging to handle due to their intricate non-convexity and non-smoothness nature and the conflicting requirements on communication efficiency and …

abstract arxiv class cs.lg data distributed federated learning orchestration paper primal privacy research server type