Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothness-Reference-Cited by-同舟云学术

Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothness

Author:

Jin Pengzhan,Lu Lu^ORCID,Tang Yifa,Karniadakis George Em^ORCID

Funder

Air Force Office of Scientific Research

National Natural Science Foundation of China

Defense Sciences Office, DARPA

U.S. Department of Energy

Ministry of Science and Technology of the People's Republic of China

Publisher

Elsevier BV

Subject

Artificial Intelligence,Cognitive Neuroscience

Reference62 articles.

1. Learning and generalization in overparameterized neural networks, going beyond two layers;Allen-Zhu,2018

2. A convergence theory for deep learning via over-parameterization;Allen-Zhu,2018

3. Fine-grained analysis of optimization and generalization for overparameterized two-layer neural networks;Arora,2019

4. Stronger generalization bounds for deep nets via a compression approach;Arora,2018

5. Spectrally-normalized margin bounds for neural networks;Bartlett,2017

Cited by 27 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Overview Frequency Principle/Spectral Bias in Deep Learning;Communications on Applied Mathematics and Computation;2024-09-04