Differentially Private Federated Learning: Servers Trustworthiness, Estimation, and Statistical Inference

arXiv:2404.16287v1 Announce Type: cross
Abstract: Differentially private federated learning is crucial for maintaining privacy in distributed environments. This paper investigates the challenges of high-dimensional estimation and inference under the constraints of differential privacy. First, we study scenarios involving an untrusted central server, demonstrating the inherent difficulties of accurate estimation in high-dimensional problems. Our findings indicate that the tight minimax rates depends on the high-dimensionality of the data even with sparsity assumptions. Second, we consider a scenario with a trusted central …

arxiv challenges constraints cs.cr cs.lg differential privacy distributed environments federated federated learning high math.st privacy private server servers stat.me stat.ml stat.th study trustworthiness under untrusted