Cover Image

Feature learning is decoupled from generalization in high capacity neural networks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Göring, Niclas Alexander, London, Charles, Erturk, Abdurrahman Hadi, Mingard, Chris, Nam, Yoonsoo, Louis, Ard A.
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A simple mean field model of feature learning
by: Göring, Niclas, et al.
Published: (2025)

Decoupling Dynamical Richness from Representation Learning: Towards Practical Measurement
by: Nam, Yoonsoo, et al.
Published: (2024)

Characterising the Inductive Biases of Neural Networks on Boolean Data
by: Mingard, Chris, et al.
Published: (2025)

Exploiting the equivalence between quantum neural networks and perceptrons
by: Mingard, Chris, et al.
Published: (2024)

An exactly solvable model for emergence and scaling laws in the multitask sparse parity problem
by: Nam, Yoonsoo, et al.
Published: (2024)

Deep neural networks have an inbuilt Occam's razor
by: Mingard, Chris, et al.
Published: (2023)

Position: Solve Layerwise Linear Models First to Understand Neural Dynamical Phenomena (Neural Collapse, Emergence, Lazy/Rich Regime, and Grokking)
by: Nam, Yoonsoo, et al.
Published: (2025)

Successive vertex orderings of connected graphs
by: Agrawal, Prarthana, et al.
Published: (2026)

Position: Many generalization measures for deep learning are fragile
by: Zhang, Shuofeng, et al.
Published: (2025)

Sufficient Conditions for Stability of Minimum-Norm Interpolating Deep ReLU Networks
by: Harzli, Ouns El, et al.
Published: (2026)

Closed-form $\ell_r$ norm scaling with data for overparameterized linear regression and diagonal linear networks under $\ell_p$ bias
by: Zhang, Shuofeng, et al.
Published: (2025)

On the generalization capacity of neural networks during generic multimodal reasoning
by: Ito, Takuya, et al.
Published: (2024)

Out-of-Domain Generalization in Dynamical Systems Reconstruction
by: Göring, Niclas, et al.
Published: (2024)

Dynamical modeling of nonlinear latent factors in multiscale neural activity with real-time inference
by: Erturk, Eray, et al.
Published: (2025)

Feature contamination: Neural networks learn uncorrelated features and fail to generalize
by: Zhang, Tianren, et al.
Published: (2024)

Bayesian continual learning and forgetting in neural networks
by: Bonnet, Djohan, et al.
Published: (2025)

Pause Tokens Strictly Increase the Expressivity of Constant-Depth Transformers
by: London, Charles, et al.
Published: (2025)

Feature learning as alignment: a structural property of gradient descent in non-linear neural networks
by: Beaglehole, Daniel, et al.
Published: (2024)

Equation identification for fluid flows via physics-informed neural networks
by: New, Alexander, et al.
Published: (2024)

Memorization capacity of deep ReLU neural networks characterized by width and depth
by: Yang, Xin, et al.
Published: (2026)

Coding schemes in neural networks learning classification tasks
by: van Meegen, Alexander, et al.
Published: (2024)

Multi-task neural networks by learned contextual inputs
by: Sandnes, Anders T., et al.
Published: (2023)

The sampling complexity of learning invertible residual neural networks
by: Li, Yuanyuan, et al.
Published: (2024)

Machine learning approaches to uncover the neural mechanisms of motivated behaviour: from ADHD to individual differences in effort and reward sensitivity
by: Trinh, Nam
Published: (2026)

Can overfitted deep neural networks in adversarial training generalize? -- An approximation viewpoint
by: Shi, Zhongjie, et al.
Published: (2024)

On the rates of convergence for learning with convolutional neural networks
by: Yang, Yunfei, et al.
Published: (2024)

Early learning of the optimal constant solution in neural networks and humans
by: Rubruck, Jirko, et al.
Published: (2024)

Emergence and scaling laws in SGD learning of shallow neural networks
by: Ren, Yunwei, et al.
Published: (2025)

Learning quadratic neural networks in high dimensions: SGD dynamics and scaling laws
by: Arous, Gérard Ben, et al.
Published: (2025)

Target noise: A pre-training based neural network initialization for efficient high resolution learning
by: Wang, Shaowen, et al.
Published: (2026)

Physics-informed neural networks for high-dimensional solutions and snaking bifurcations in nonlinear lattices
by: Shahab, Muhammad Luthfi, et al.
Published: (2025)

Progressive multi-fidelity learning with neural networks for physical system predictions
by: Conti, Paolo, et al.
Published: (2025)

The impact of allocation strategies in subset learning on the expressive power of neural networks
by: Schlisselberg, Ofir, et al.
Published: (2025)

Computing high-dimensional optimal transport by flow neural networks
by: Xu, Chen, et al.
Published: (2023)

Convergence of gradient flow for learning convolutional neural networks
by: Diederen, Jona-Maria, et al.
Published: (2026)

Automatic debiasing of neural networks via moment-constrained learning
by: Hines, Christian L., et al.
Published: (2024)

Posterior concentrations of fully-connected Bayesian neural networks with general priors on the weights
by: Kong, Insung, et al.
Published: (2024)

Adversarially robust generalization theory via Jacobian regularization for deep neural networks
by: Wu, Dongya, et al.
Published: (2024)

Memory capacity of two layer neural networks with smooth activations
by: Madden, Liam, et al.
Published: (2023)

High-dimensional learning of narrow neural networks
by: Cui, Hugo
Published: (2024)