Private Networked Federated Learning for Nonsmooth Objectives

arXiv:2306.14012v2 Announce Type: replace-cross
Abstract: This paper develops a networked federated learning algorithm to solve nonsmooth objective functions. To guarantee the confidentiality of the participants with respect to each other and potential eavesdroppers, we use the zero-concentrated differential privacy notion (zCDP). Privacy is achieved by perturbing the outcome of the computation at each client with a variance-decreasing Gaussian noise. ZCDP allows for better accuracy than the conventional $(\epsilon, \delta)$-DP and stronger guarantees than the more recent R\'enyi-DP by assuming adversaries …

abstract algorithm arxiv computation differential differential privacy federated learning functions math.oc notion paper privacy solve stat.ml type