Weighted distributed differential privacy ERM: Convex and non-convex

Distributed machine learning allows different parties to learn a single model over all data sets without disclosing their own data. In this paper, we propose a weighted distributed differentially private (WD-DP) empirical risk minimization (ERM) method to train a model in distributed setting, consid...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Computers & security 2021-07, Vol.106, p.102275, Article 102275
Hauptverfasser:	Kang, Yilin, Liu, Yong, Niu, Ben, Wang, Weiping
Format:	Artikel
Sprache:	eng
Schlagworte:	Clients Convexity Cybersecurity Datasets Differential privacy Distributed machine learning Empirical analysis Empirical risk minimization Machine learning Polyak-Łojasiewicz condition Privacy Strongly convex Weighted parties
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!