arXiv Machine Learning June 26, 2026 By Tao Luo, Zheng Ma, Zhi-Qin John Xu, Yaoyu Zhang

Theory of the Frequency Principle for General Deep Neural Networks

Read the original on arXiv Machine Learning →

arXiv:1906. 09235v3 Announce Type: replace Abstract: Along with fruitful applications of Deep Neural Networks (DNNs) to realistic problems, recently, some empirical studies of DNNs reported a universal phenomenon of Frequency Principle (F-Principle): a DNN tends to learn a target function from low to high frequencies during the training.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jul 13

Principles of Lipschitz continuity in neural networks

arXiv:2602. 04078v2 Announce Type: replace-cross Abstract: Deep learning has achieved remarkable success across a wide range of domains, significantly expanding the frontiers of what is achievable in artificial intelligence.

By R\'ois\'in Luo

arXiv Machine Learning

Jun 16

RepNet: Tackling spectral bias in deep neural networks via parameter reparameterization

arXiv:2606. 16575v1 Announce Type: new Abstract: Deep neural networks (DNNs) have achieved remarkable success in scientific computing, yet they often suffer from spectral bias in capturing oscillatory and multiscale behaviors.

By Yong Wang, Tao Zhou, Xuhui Meng

safety

arXiv Machine Learning

Jun 25

Fourier Multi-Component and Multi-Layer Neural Networks: Unlocking High-Frequency Potential

arXiv:2502. 18959v4 Announce Type: replace Abstract: The architecture of a neural network and the choice of its activation function are both fundamental to its performance.

By Shijun Zhang, Hongkai Zhao, Yimin Zhong, Haomin Zhou

benchmarks safety

arXiv AI

Jun 8

Generalization in Deep Neural Networks: Minimax Rates for Gradient Methods

arXiv:2606. 06772v1 Announce Type: cross Abstract: Understanding the generalization performance of over-parameterized neural networks has become a central topic in deep learning theory.

By Junyu Zhou, Puyu Wang, Yunwen Lei, Marius Kloft, Yiming Ying

arXiv Machine Learning

Jun 19

Statistical Properties of Training & Generalization

arXiv:2606. 20299v1 Announce Type: cross Abstract: Deep learning has managed to evade numerous intuitions from classical statistics to achieve unprecedented performance on a number of real-world tasks.

By Itay Lavie, Noam Levi, Yonatan Kahn

arXiv Machine Learning

Jul 24

Statistical physics of deep learning: Optimal learning of a multi-layer perceptron near interpolation

arXiv:2510. 24616v4 Announce Type: replace-cross Abstract: For four decades statistical physics has been providing a framework to analyse neural networks.

By Jean Barbier, Francesco Camilli, Minh-Toan Nguyen, Mauro Pastore, Rudy Skerk

rag

Related stories

Principles of Lipschitz continuity in neural networks

RepNet: Tackling spectral bias in deep neural networks via parameter reparameterization

Fourier Multi-Component and Multi-Layer Neural Networks: Unlocking High-Frequency Potential

Generalization in Deep Neural Networks: Minimax Rates for Gradient Methods

Statistical Properties of Training & Generalization

Statistical physics of deep learning: Optimal learning of a multi-layer perceptron near interpolation