Distributed Mean Estimation with Limited Communication

Motivated by the need for distributed learning and optimization algorithms with low communication cost, we study communication efficient algorithms for distributed mean estimation. Unlike previous works, we make no probabilistic assumptions on the data. We first show that for $d$ dimensional data wi...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Suresh, Ananda Theertha, Yu, Felix X, Kumar, Sanjiv, McMahan, H. Brendan
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!