Scaling Laws in Linear Regression: Compute, Parameters, and Data

Empirically, large-scale deep learning models often satisfy a neural scaling law: the test error of the trained model improves polynomially as the model size and data size grow. However, conventional wisdom suggests the test error consists of approximation, bias, and variance errors, where the varia...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Lin, Licong, Wu, Jingfeng, Kakade, Sham M, Bartlett, Peter L, Lee, Jason D
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Artificial Intelligence Computer Science - Learning Mathematics - Statistics Theory Statistics - Machine Learning Statistics - Theory
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!