DIFF2: Differential Private Optimization via Gradient Differences for Nonconvex Distributed Learning

Differential private optimization for nonconvex smooth objective is considered. In the previous work, the best known utility bound is \(\widetilde O(\sqrt{d}/(n\varepsilon_\mathrm{DP}))\) in terms of the squared full gradient norm, which is achieved by Differential Private Gradient Descent (DP-GD) a...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-06
Hauptverfasser:	Murata, Tomoya, Suzuki, Taiji
Format:	Artikel
Sprache:	eng
Schlagworte:	Optimization Privacy Subroutines
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!