Cover Image

The Spectral Bias of Shallow Neural Network Learning is Shaped by the Choice of Non-linearity

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sahs, Justin, Pyle, Ryan, Anselmi, Fabio, Patel, Ankit
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Quotient Geometry, Effective Curvature, and Implicit Bias in Simple Shallow Neural Networks
by: Dong, Hang-Cheng, et al.
Published: (2026)

Addressing Spectral Bias of Deep Neural Networks by Multi-Grade Deep Learning
by: Fang, Ronglong, et al.
Published: (2024)

Towards Initialization-dependent and Non-vacuous Generalization Bounds for Overparameterized Shallow Neural Networks
by: Lei, Yunwen, et al.
Published: (2026)

SBS: Enhancing Parameter-Efficiency of Neural Representations for Neural Networks via Spectral Bias Suppression
by: Xie, Qihu, et al.
Published: (2025)

Implicit Regularization via Spectral Neural Networks and Non-linear Matrix Sensing
by: Chu, Hong T. M., et al.
Published: (2024)

Shape-aware Graph Spectral Learning
by: Xu, Junjie, et al.
Published: (2023)

On the Rate of Convergence of GD in Non-linear Neural Networks: An Adversarial Robustness Perspective
by: Smorodinsky, Guy, et al.
Published: (2026)

How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks
by: Stupariu, Teodor-Mihai, et al.
Published: (2026)

Iterative Refinement Neural Operators are Learned Fixed-Point Solvers: A Principled Approach to Spectral Bias Mitigation
by: Liu, Xiaotian, et al.
Published: (2026)

Spectral Higher-Order Neural Networks
by: Peri, Gianluca, et al.
Published: (2026)

Spatio-Spectral Graph Neural Networks
by: Geisler, Simon, et al.
Published: (2024)

From Shallow Bayesian Neural Networks to Gaussian Processes: General Convergence, Identifiability and Scalable Inference
by: de Araújo, Gracielle Antunes, et al.
Published: (2026)

From Alexnet to Transformers: Measuring the Non-linearity of Deep Neural Networks with Affine Optimal Transport
by: Bouniot, Quentin, et al.
Published: (2023)

Frequency maps reveal the correlation between Adversarial Attacks and Implicit Bias
by: Basile, Lorenzo, et al.
Published: (2023)

Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime
by: Defilippis, Leonardo, et al.
Published: (2025)

Piecewise Constant Spectral Graph Neural Network
by: Martirosyan, Vahan, et al.
Published: (2025)

Spectral Greedy Coresets for Graph Neural Networks
by: Ding, Mucong, et al.
Published: (2024)

Do Deep Neural Network Solutions Form a Star Domain?
by: Sonthalia, Ankit, et al.
Published: (2024)

Eigenspectrum Analysis of Neural Networks without Aspect Ratio Bias
by: Hu, Yuanzhe, et al.
Published: (2025)

A Relational Inductive Bias for Dimensional Abstraction in Neural Networks
by: Campbell, Declan, et al.
Published: (2024)

Dynamic Spectral Backpropagation for Efficient Neural Network Training
by: Muthuraman, Mannmohan
Published: (2025)

Non-linear Welfare-Aware Strategic Learning
by: Xie, Tian, et al.
Published: (2024)

Machine-Learning-Enhanced Non-Invasive Testing for MASLD Fibrosis: Shallow-Deep Neural Networks Versus FIB-4, Tabular Foundation Models, and Large Language Models
by: Angelakis, Athanasios, et al.
Published: (2026)

Uncovering the Spectral Bias in Diagonal State Space Models
by: Solozabal, Ruben, et al.
Published: (2025)

Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset
by: Galashov, Alexandre, et al.
Published: (2024)

Closed-Form Interpretation of Neural Network Latent Spaces with Symbolic Gradients
by: Wetzel, Sebastian J., et al.
Published: (2024)

Rethinking Spectral Graph Neural Networks with Spatially Adaptive Filtering
by: Guo, Jingwei, et al.
Published: (2024)

Non-convolutional Graph Neural Networks
by: Wang, Yuanqing, et al.
Published: (2024)

Teasing Apart Architecture and Initial Weights as Sources of Inductive Bias in Neural Networks
by: Bencomo, Gianluca, et al.
Published: (2025)

Autocorrelation Reintroduces Spectral Bias in KANs for Time Series Forecasting
by: Zeng, Chen, et al.
Published: (2026)

Spectral Theory for Edge Pruning in Asynchronous Recurrent Graph Neural Networks
by: Bessone, Nicolas
Published: (2025)

Neural Approaches to SAT Solving: Design Choices and Interpretability
by: Mojžíšek, David, et al.
Published: (2025)

PRISM: Structured Optimization via Anisotropic Spectral Shaping
by: Yang, Yujie
Published: (2026)

Non-Euclidean Spatial Graph Neural Network
by: Zhang, Zheng, et al.
Published: (2023)

Deep Minds and Shallow Probes
by: Lee, Su Hyeong, et al.
Published: (2026)

Does Your Neural Network Extrapolate? Feature Engineering as Identifiability Bias for OOD Generalization
by: Aguilar, Leonel, et al.
Published: (2026)

Approaching Deep Learning through the Spectral Dynamics of Weights
by: Yunis, David, et al.
Published: (2024)

Towards Expressive Spectral-Temporal Graph Neural Networks for Time Series Forecasting
by: Jin, Ming, et al.
Published: (2023)

Generalized Learning of Coefficients in Spectral Graph Convolutional Networks
by: Coşkun, Mustafa, et al.
Published: (2024)

Leveraging Manifold Embeddings for Enhanced Graph Transformer Representations and Learning
by: Jyothish, Ankit, et al.
Published: (2025)