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...
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: | |
Online Access: | https://doi.org/10.1088/2632-2153/ad13ba |
Similar Items
-
Counterexamples for Noise Models of Stochastic Gradients
by: Vivak Patel
Published: (2023-12-01) -
Recent Advances in Stochastic Gradient Descent in Deep Learning
by: Yingjie Tian, et al.
Published: (2023-01-01) -
Damped Newton Stochastic Gradient Descent Method for Neural Networks Training
by: Jingcheng Zhou, et al.
Published: (2021-06-01) -
A Geometric Interpretation of Stochastic Gradient Descent Using Diffusion Metrics
by: Rita Fioresi, et al.
Published: (2020-01-01) -
Distributed Stochastic Gradient Descent With Compressed and Skipped Communication
by: Tran Thi Phuong, et al.
Published: (2023-01-01)