Stochastic gradient descent with random label noises: doubly stochastic models and inference stabilizer

Stochastic gradient descent with random label noises: doubly stochastic models and inference stabilizer

Random label noise (or observational noise) widely exists in practical machine learning settings. While previous studies primarily focused on the effects of label noise to the performance of learning, our work intends to investigate the implicit regularization effects of label noise, under mini-batc...

Full description

Bibliographic Details
Main Authors: Haoyi Xiong, Xuhong Li, Boyang Yu, Dongrui Wu, Zhanxing Zhu, Dejing Dou
Format: Article
Language:English
Published: IOP Publishing 2024-01-01
Series:Machine Learning: Science and Technology
Subjects:
stochastic gradient descent
continuous-time analysis
dynamical systems
Online Access:https://doi.org/10.1088/2632-2153/ad13ba

Internet

https://doi.org/10.1088/2632-2153/ad13ba

Similar Items