Damped Newton Stochastic Gradient Descent Method for Neural Networks Training
First-order methods such as stochastic gradient descent (SGD) have recently become popular optimization methods to train deep neural networks (DNNs) for good generalization; however, they need a long training time. Second-order methods which can lower the training time are scarcely used on account o...
Main Authors: | Jingcheng Zhou, Wei Wei, Ruizhi Zhang, Zhiming Zheng |
---|---|
Format: | Article |
Sprog: | English |
Udgivet: |
MDPI AG
2021-06-01
|
Serier: | Mathematics |
Fag: | |
Online adgang: | https://www.mdpi.com/2227-7390/9/13/1533 |
Lignende værker
-
Adaptive Stochastic Gradient Descent Method for Convex and Non-Convex Optimization
af: Ruijuan Chen, et al.
Udgivet: (2022-11-01) -
The Improved Stochastic Fractional Order Gradient Descent Algorithm
af: Yang Yang, et al.
Udgivet: (2023-08-01) -
Recent Advances in Stochastic Gradient Descent in Deep Learning
af: Yingjie Tian, et al.
Udgivet: (2023-01-01) -
A Geometric Interpretation of Stochastic Gradient Descent Using Diffusion Metrics
af: Rita Fioresi, et al.
Udgivet: (2020-01-01) -
Stochastic gradient descent with random label noises: doubly stochastic models and inference stabilizer
af: Haoyi Xiong, et al.
Udgivet: (2024-01-01)