Accelerating Distributed Optimization: A Primal-Dual Perspective on Local Steps

In distributed machine learning, efficient training across multiple agents with different data distributions poses significant challenges. Even with a centralized coordinator, current algorithms that achieve optimal communication complexity typically require either large minibatches or compromise on...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-08
Hauptverfasser:	Yang, Junchi, Yildirim, Murat, Qiu, Feng
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Communication Complexity Machine learning Optimization
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!