Imagen de Portada

How does feature learning reshape the function space?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lobo, João, Loureiro, Bruno, Tran-Than, Long, Liu, Fanghui
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Dimension-free deterministic equivalents and scaling laws for random feature regression
por: Defilippis, Leonardo, et al.
Publicado: (2024)

A Novel Spatiotemporal Coupling Graph Convolutional Network
por: Bi, Fanghui
Publicado: (2024)

Asymptotics of feature learning in two-layer networks after one gradient-step
por: Cui, Hugo, et al.
Publicado: (2024)

Optimal scaling laws in learning hierarchical multi-index models
por: Defilippis, Leonardo, et al.
Publicado: (2026)

Mockingbird: How does LLM perform in general machine learning tasks?
por: Jia, Haoyu, et al.
Publicado: (2025)

The Hidden Power of Normalization Layers in Neural Networks: Exponential Capacity Control
por: Than, Khoat
Publicado: (2025)

Escaping mediocrity: how two-layer networks learn hard generalized linear models with SGD
por: Arnaboldi, Luca, et al.
Publicado: (2023)

Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks
por: Liu, Fanghui, et al.
Publicado: (2024)

Breaking the curse of dimensionality for linear rules: optimal predictors over the ellipsoid
por: Ayme, Alexis, et al.
Publicado: (2025)

Kernel ridge regression under power-law data: spectrum and generalization
por: Wortsman, Arie, et al.
Publicado: (2025)

How Two-Layer Neural Networks Learn, One (Giant) Step at a Time
por: Dandi, Yatin, et al.
Publicado: (2023)

Self-Regularized Learning Methods
por: Schölpple, Max, et al.
Publicado: (2026)

LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently
por: Zhang, Yuanhe, et al.
Publicado: (2025)

Using Synthetic Data to estimate the True Error is theoretically and practically doable
por: Thanh, Hai Hoang, et al.
Publicado: (2025)

End-to-end Kernel Learning via Generative Random Fourier Features
por: Fang, Kun, et al.
Publicado: (2020)

High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization
por: Chen, Yihang, et al.
Publicado: (2024)

Physics-Informed Design of Input Convex Neural Networks for Consistency Optimal Transport Flow Matching
por: Song, Fanghui, et al.
Publicado: (2025)

Graph Clustering with Cross-View Feature Propagation
por: Duan, Zhixuan, et al.
Publicado: (2024)

Annealing in variational inference mitigates mode collapse: A theoretical study on Gaussian mixtures
por: Fogliani, Luigi, et al.
Publicado: (2026)

KOPPA: Improving Prompt-based Continual Learning with Key-Query Orthogonal Projection and Prototype-based One-Versus-All
por: Tran, Quyen, et al.
Publicado: (2023)

Provably Improving Generalization of Few-Shot Models with Synthetic Data
por: Nguyen, Lan-Cuong, et al.
Publicado: (2025)

How does over-squashing affect the power of GNNs?
por: Di Giovanni, Francesco, et al.
Publicado: (2023)

Gentle Local Robustness implies Generalization
por: Than, Khoat, et al.
Publicado: (2024)

How does Bayesian Sampling help Membership Inference Attacks?
por: Liu, Zhenlong, et al.
Publicado: (2025)

The $φ$ Curve: The Shape of Generalization through the Lens of Norm-based Capacity Control
por: Wang, Yichen, et al.
Publicado: (2025)

Learning Scalable Model Soup on a Single GPU: An Efficient Subspace Training Strategy
por: Li, Tao, et al.
Publicado: (2024)

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

What model does MuZero learn?
por: He, Jinke, et al.
Publicado: (2023)

How does ion temperature gradient turbulence depend on magnetic geometry? Insights from data and machine learning
por: Landreman, Matt, et al.
Publicado: (2025)

Enhancing Visual Feature Attribution via Weighted Integrated Gradients
por: Tuan, Kien Tran Duc, et al.
Publicado: (2025)

Statistical Learning Theory in Lean 4: Empirical Processes from Scratch
por: Zhang, Yuanhe, et al.
Publicado: (2026)

Beyond topography: Topographic regularization improves robustness and reshapes representations in convolutional neural networks
por: Truong, Nhut, et al.
Publicado: (2025)

A Noise Sensitivity Exponent Controls Large Statistical-to-Computational Gaps in Single- and Multi-Index Models
por: Defilippis, Leonardo, et al.
Publicado: (2026)

Generalization of Scaled Deep ResNets in the Mean-Field Regime
por: Chen, Yihang, et al.
Publicado: (2024)

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

How does the brain compute with probabilities?
por: Haefner, Ralf M., et al.
Publicado: (2024)

Fast Escape, Slow Convergence: Learning Dynamics of Phase Retrieval under Power-Law Data
por: Braun, Guillaume, et al.
Publicado: (2025)

FeatMap: Understanding image manipulation in the feature space and its implications for feature space geometry
por: Krey, Elias B., et al.
Publicado: (2026)

A Bayesian explanation of machine learning models based on modes and functional ANOVA
por: Long, Quan
Publicado: (2024)

Heterogeneous transfer learning for high-dimensional regression with feature mismatch
por: Chang, Jae Ho, et al.
Publicado: (2024)