A0677
Title: Privacy protection and statistical efficiency trade-off for federated learning
Authors: Haobo Qi - Beijing Normal University (China) [presenting]
Abstract: Federated learning is a novel framework for distributed learning, which aims to break isolated data islands as well as protect data privacy. To further prevent privacy leakage by specially crafted attacks, differential privacy is often integrated. Although differential privacy effectively secures sensitive information, it can reduce the statistical efficiency of the resulting estimators. This leads to a trade-off relationship between statistical efficiency and privacy protection. To theoretically understand this relationship, the classic linear regression model and a noise-adding federated gradient descent algorithm are started with. Its numerical convergence properties and asymptotic properties are rigorously studied. This results in fruitful insights into the trade-off relationship between statistical efficiency and privacy protection. Guided by these theoretical understandings, a Polyak-Ruppert type averaged estimator is further developed, which can achieve good statistical efficiency with guaranteed privacy protection. Extensive simulation studies are presented to corroborate the theoretical results. Finally, the application of the proposed method is illustrated on an enterprise community dataset.
