Loading [MathJax]/jax/output/HTML-CSS/config.js
Journals
Resources
About Us
Open Access
Go to previous page

Theory of the Frequency Principle for General Deep Neural Networks

Theory of the Frequency Principle for General Deep Neural Networks

Year:    2021

Author:    Tao Luo, Zheng Ma, Zhi-Qin John Xu, Yaoyu Zhang

CSIAM Transactions on Applied Mathematics, Vol. 2 (2021), Iss. 3 : pp. 484–507

Abstract

Along with fruitful applications of Deep Neural Networks (DNNs) to realistic problems, recently, empirical studies reported a universal phenomenon of Frequency Principle (F-Principle), that is, a DNN tends to learn a target function from low to high frequencies during the training. The F-Principle has been very useful in providing both qualitative and quantitative understandings of DNNs. In this paper, we rigorously investigate the F-Principle for the training dynamics of a general DNN at three stages: initial stage, intermediate stage, and final stage. For each stage, a theorem is provided in terms of proper quantities characterizing the F-Principle. Our results are general in the sense that they work for multilayer networks with general activation functions, population densities of data, and a large class of loss functions. Our work lays a theoretical foundation of the F-Principle for a better understanding of the training process of DNNs.

You do not have full access to this article.

Already a Subscriber? Sign in as an individual or via your institution

Journal Article Details

Publisher Name:    Global Science Press

Language:    English

DOI:    https://doi.org/10.4208/csiam-am.SO-2020-0005

CSIAM Transactions on Applied Mathematics, Vol. 2 (2021), Iss. 3 : pp. 484–507

Published online:    2021-01

AMS Subject Headings:    Global Science Press

Copyright:    COPYRIGHT: © Global Science Press

Pages:    24

Keywords:    Frequency principle Deep Neural Networks dynamical system training process.

Author Details

Tao Luo Email

Zheng Ma Email

Zhi-Qin John Xu Email

Yaoyu Zhang Email

  1. Spectral-DP: Differentially Private Deep Learning through Spectral Perturbation and Filtering

    Feng, Ce | Xu, Nuo | Wen, Wujie | Venkitasubramaniam, Parv | Ding, Caiwen

    2023 IEEE Symposium on Security and Privacy (SP), (2023), P.1944

    https://doi.org/10.1109/SP46215.2023.10179457 [Citations: 1]
  2. FSGformer: Frequency Separation and Guidance Transformer for Pansharpening

    Liu, Qian | Zhao, Xiangyu | Qin, You | Li, Lanyu | Liu, Junmin

    IEEE Transactions on Geoscience and Remote Sensing, Vol. 63 (2025), Iss. P.1

    https://doi.org/10.1109/TGRS.2025.3544755 [Citations: 0]
  3. No Time to Train: Empowering Non-Parametric Networks for Few-Shot 3D Scene Segmentation

    Zhu, Xiangyang | Zhang, Renrui | He, Bowei | Guo, Ziyu | Liu, Jiaming | Xiao, Han | Fu, Chaoyou | Dong, Hao | Gao, Peng

    2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2024), P.3838

    https://doi.org/10.1109/CVPR52733.2024.00368 [Citations: 2]
  4. Bearing Fault Diagnosis Method Based on Attention Mechanism and Multi-Channel Feature Fusion

    Gao, Hongfeng | Ma, Jie | Zhang, Zhonghang | Cai, Chaozhi

    IEEE Access, Vol. 12 (2024), Iss. P.45011

    https://doi.org/10.1109/ACCESS.2024.3381618 [Citations: 6]
  5. Implicit Regularization of Dropout

    Zhang, Zhongwang | Xu, Zhi-Qin John

    IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 46 (2024), Iss. 6 P.4206

    https://doi.org/10.1109/TPAMI.2024.3357172 [Citations: 3]
  6. Overview Frequency Principle/Spectral Bias in Deep Learning

    Xu, Zhi-Qin John | Zhang, Yaoyu | Luo, Tao

    Communications on Applied Mathematics and Computation, Vol. (2024), Iss.

    https://doi.org/10.1007/s42967-024-00398-7 [Citations: 5]
  7. Probabilistic quantile multiple fourier feature network for lake temperature forecasting: incorporating pinball loss for uncertainty estimation

    Liu, Siyuan | Deng, Jiaxin | Yuan, Jin | Li, Weide | Li, Xi’an | Xu, Jing | Zhang, Shaotong | Wu, Jinran | Wang, You-Gan

    Earth Science Informatics, Vol. 17 (2024), Iss. 6 P.5135

    https://doi.org/10.1007/s12145-024-01448-7 [Citations: 0]
  8. Data-driven parametric soliton-rogon state transitions for nonlinear wave equations using deep learning with Fourier neural operator

    Zhong, Ming | Yan, Zhenya | Tian, Shou-Fu

    Communications in Theoretical Physics, Vol. 75 (2023), Iss. 2 P.025001

    https://doi.org/10.1088/1572-9494/acab55 [Citations: 5]
  9. A novel fast spectral computed tomography reconstruction method with spectral windowed analytical iterative technique

    Pan, Huiying | Jiang, Xu | Shi, Ligen | Zhang, Wei | Zhao, Xing

    Optics and Lasers in Engineering, Vol. 189 (2025), Iss. P.108935

    https://doi.org/10.1016/j.optlaseng.2025.108935 [Citations: 0]
  10. On understanding and overcoming spectral biases of deep neural network learning methods for solving PDEs

    Xu, Zhi-Qin John | Zhang, Lulu | Cai, Wei

    Journal of Computational Physics, Vol. 530 (2025), Iss. P.113905

    https://doi.org/10.1016/j.jcp.2025.113905 [Citations: 0]
  11. Unsupervised Deep Learning for Ground Roll and Scattered Noise Attenuation

    Liu, Dawei | Sacchi, Mauricio D. | Wang, Xiaokai | Chen, Wenchao

    IEEE Transactions on Geoscience and Remote Sensing, Vol. 61 (2023), Iss. P.1

    https://doi.org/10.1109/TGRS.2023.3325324 [Citations: 15]
  12. Gaussian low‐pass channel attention convolution network for RF fingerprinting

    Zhang, Shunjie | Wu, Tianhao | Wang, Wei | Zhan, Ronghui | Zhang, Jun

    Electronics Letters, Vol. 59 (2023), Iss. 12

    https://doi.org/10.1049/ell2.12846 [Citations: 1]
  13. Minimalism is King! High-Frequency Energy-Based Screening for Data-Efficient Backdoor Attacks

    Xun, Yuan | Jia, Xiaojun | Gu, Jindong | Liu, Xinwei | Guo, Qing | Cao, Xiaochun

    IEEE Transactions on Information Forensics and Security, Vol. 19 (2024), Iss. P.4560

    https://doi.org/10.1109/TIFS.2024.3380821 [Citations: 1]
  14. Input gradient annealing neural network for solving Fokker-Planck equations with low temperature

    Hang, Liangkai | Hu, Dan | Xu, Zhi-Qin John

    Journal of Computational Physics, Vol. 524 (2025), Iss. P.113688

    https://doi.org/10.1016/j.jcp.2024.113688 [Citations: 0]
  15. HMDM: A hybrid GM model-based and MHSA-GRU data-driven method for remaining useful life prediction of rolling bearings

    Zhao, Qiwu | Zhang, Xiaoli

    Journal of Vibration and Control, Vol. (2024), Iss.

    https://doi.org/10.1177/10775463241273080 [Citations: 0]
  16. Regularize implicit neural representation by itself

    Li, Zhemin | Wang, Hongxia | Meng, Deyu

    2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2023), P.10280

    https://doi.org/10.1109/CVPR52729.2023.00991 [Citations: 4]
  17. Learning Gabor Texture Features for Fine-Grained Recognition

    Zhu, Lanyun | Chen, Tianrun | Yin, Jianxiong | See, Simon | Liu, Jun

    2023 IEEE/CVF International Conference on Computer Vision (ICCV), (2023), P.1621

    https://doi.org/10.1109/ICCV51070.2023.00156 [Citations: 13]
  18. Optimization of Physics-Informed Neural Networks for Solving the Nolinear Schrödinger Equation

    Chuprov, I. | Gao, Jiexing | Efremenko, D. | Kazakov, E. | Buzaev, F. | Zemlyakov, V.

    Doklady Mathematics, Vol. 108 (2023), Iss. S2 P.S186

    https://doi.org/10.1134/S1064562423701120 [Citations: 3]
  19. Towards Inadequately Pre-trained Models in Transfer Learning

    Deng, Andong | Li, Xingjian | Hu, Di | Wang, Tianyang | Xiong, Haoyi | Xu, Cheng-Zhong

    2023 IEEE/CVF International Conference on Computer Vision (ICCV), (2023), P.19340

    https://doi.org/10.1109/ICCV51070.2023.01777 [Citations: 4]