Making Scalable Meta Learning Practical

Despite its flexibility to learn diverse inductive biases in machine learning programs, meta learning (i.e., learning to learn) has long been recognized to suffer from poor scalability due to its tremendous compute/memory costs, training instability, and a lack of efficient distributed training supp...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-10
Hauptverfasser:	Choe, Sang Keun, Mehta, Sanket Vaibhav, Ahn, Hwijeen, Neiswanger, Willie, Xie, Pengtao, Strubell, Emma, Xing, Eric
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Image classification Large language models Learning programs Machine learning Optimization
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!