Recycling Scraps: Improving Private Learning by Leveraging Intermediate Checkpoints

In this work, we focus on improving the accuracy-variance trade-off for state-of-the-art differentially private machine learning (DP ML) methods. First, we design a general framework that uses aggregates of intermediate checkpoints \emph{during training} to increase the accuracy of DP ML techniques....

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Shejwalkar, Virat, Ganesh, Arun, Mathews, Rajiv, Mu, Yarong, Song, Shuang, Thakkar, Om, Thakurta, Abhradeep, Zheng, Xinyi
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Cryptography and Security Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!