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...

Full description

Saved in:
Bibliographic Details
Main Authors: Youngkyoung Bae, Yeongwoo Song, Hawoong Jeong
Format: Article
Language:English
Published: IOP Publishing 2025-01-01
Series:Machine Learning: Science and Technology
Subjects:
Online Access:https://doi.org/10.1088/2632-2153/adbc46
Tags: Add Tag
No Tags, Be the first to tag this record!