Stochastic Resetting Mitigates Latent Gradient Bias of SGD from Label Noise

Giving up and starting over may seem wasteful in many situations such as searching for a target or training deep neural networks (DNNs). Our study, though, demonstrates that resetting from a checkpoint can significantly improve generalization performance when training DNNs with noisy labels. In the...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-11
Hauptverfasser:	Bae, Youngkyoung, Song, Yeongwoo, Jeong, Hawoong
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Labels Neural networks Restarting
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!