English
Related papers

Related papers: Is the Frequency Principle always valid?

200 papers

An intriguing phenomenon observed during training neural networks is the spectral bias, which states that neural networks are biased towards learning less complex functions. The priority of learning functions with low complexity might be at…

Machine Learning · Computer Science 2020-10-06 Yuan Cao , Zhiying Fang , Yue Wu , Ding-Xuan Zhou , Quanquan Gu

In this work, we study the nonlinear dynamics of a shallow neural network trained with mean-squared loss and leaky ReLU activation. Under Gaussian inputs and equal layer width k, (1) we establish, based on the equivariant gradient degree, a…

Optimization and Control · Mathematics 2025-10-30 Jingzhou Liu

The convolutional layers are core building blocks of neural network architectures. In general, a convolutional filter applies to the entire frequency spectrum of the input data. We explore artificially constraining the frequency spectra of…

Machine Learning · Computer Science 2019-11-22 Adam Dziedzic , John Paparrizos , Sanjay Krishnan , Aaron Elmore , Michael Franklin

A recurrent neural network model of phonological pattern learning is proposed. The model is a relatively simple neural network with one recurrent layer, and displays biases in learning that mimic observed biases in human learning.…

Computation and Language · Computer Science 2024-05-31 Amanda Doucette

Minimizing PDE-residual losses is a common strategy to promote physical consistency in neural operators. However, standard formulations often lack variational correctness, meaning that small residuals do not guarantee small solution errors…

Numerical Analysis · Mathematics 2025-12-25 Yuan Qiu , Wolfgang Dahmen , Peng Chen

We investigate the spectral properties of linear-width feed-forward neural networks, where the sample size is asymptotically proportional to network width. Empirically, we show that the spectra of weight in this high dimensional regime are…

Machine Learning · Computer Science 2023-11-09 Zhichao Wang , Andrew Engel , Anand Sarwate , Ioana Dumitriu , Tony Chiang

Understanding the learning dynamics and inductive bias of neural networks (NNs) is hindered by the opacity of the relationship between NN parameters and the function represented. We propose reparametrizing ReLU NNs as continuous piecewise…

Machine Learning · Computer Science 2020-08-06 Justin Sahs , Ryan Pyle , Aneel Damaraju , Josue Ortega Caro , Onur Tavaslioglu , Andy Lu , Ankit Patel

Gradient-based optimization has been a cornerstone of machine learning that enabled the vast advances of Artificial Intelligence (AI) development over the past decades. However, this type of optimization requires differentiation, and with…

Operator learning is a data-driven approximation of mappings between infinite-dimensional function spaces, such as the solution operators of partial differential equations. Kernel-based operator learning can offer accurate, theoretically…

Machine Learning · Computer Science 2025-12-22 Xinyue Yu , Hayden Schaeffer

Understanding the time evolution of physical systems is crucial to revealing fundamental characteristics that are hidden in frequency domain. In optical science, high-quality resonance cavities and enhanced interactions with matters are at…

Optics · Physics 2021-09-22 Yingheng Tang , Jichao Fan , Xinwei Li , Jianzhu Ma , Minghao Qi , Cunxi Yu , Weilu Gao

Despite their ability to represent highly expressive functions, deep learning models seem to find simple solutions that generalize surprisingly well. Spectral bias -- the tendency of neural networks to prioritize learning low frequency…

Machine Learning · Computer Science 2022-09-30 Sara Fridovich-Keil , Raphael Gontijo-Lopes , Rebecca Roelofs

We explore the ability of overparameterized shallow ReLU neural networks to learn Lipschitz, nondifferentiable, bounded functions with additive noise when trained by Gradient Descent (GD). To avoid the problem that in the presence of noise,…

Machine Learning · Computer Science 2023-04-07 Ilja Kuzborskij , Csaba Szepesvári

The current paradigm of training deep neural networks for classification tasks includes minimizing the empirical risk that pushes the training loss value towards zero, even after the training error has been vanished. In this terminal phase…

Machine Learning · Computer Science 2024-06-07 Hien Dang , Tho Tran , Tan Nguyen , Nhat Ho

To understand the training dynamics of neural networks (NNs), prior studies have considered the infinite-width mean-field (MF) limit of two-layer NN, establishing theoretical guarantees of its convergence under gradient flow training as…

Machine Learning · Computer Science 2022-10-31 Zhengdao Chen , Eric Vanden-Eijnden , Joan Bruna

The increasing penetration of distributed energy resources (DERs) will decrease the rotational inertia of the power system and further degrade the system frequency stability. To address the above issues, this paper leverages the advanced…

Systems and Control · Electrical Eng. & Systems 2023-04-24 Linwei Sang , Yinliang Xu , Zhongkai Yi , Lun Yang , Huan Long , Hongbin Sun

Effective hyper-parameter tuning is essential to guarantee the performance that neural networks have come to be known for. In this work, a principled approach to choosing the learning rate is proposed for shallow feedforward neural…

Machine Learning · Computer Science 2020-10-01 Thulasi Tholeti , Sheetal Kalyani

The push to train ever larger neural networks has motivated the study of initialization and training at large network width. A key challenge is to scale training so that a network's internal representations evolve nontrivially at all…

Machine Learning · Computer Science 2024-05-15 Greg Yang , James B. Simon , Jeremy Bernstein

Neural operators learn to map initial conditions to the terminal solution of partial differential equations (PDEs), providing a surrogate for the full operator mapping. This enables rapid prediction across different input configurations.…

Machine Learning · Computer Science 2026-05-14 Runlong Xie , An Luo

Learning a task induces connectivity changes in neural circuits, thereby changing their dynamics. To elucidate task related neural dynamics we study trained Recurrent Neural Networks. We develop a Mean Field Theory for Reservoir Computing…

Neurons and Cognition · Quantitative Biology 2017-06-28 Alexander Rivkind , Omri Barak

Many existing interpretation methods of convolutional neural networks (CNNs) mainly analyze in spatial domain, yet model interpretability in frequency domain has been rarely studied. To the best of our knowledge, there is no study on the…

Computer Vision and Pattern Recognition · Computer Science 2020-03-02 Zhongfan Jia , Chenglong Bao , Kaisheng Ma