Cover Image

Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nguyen, Minh-Toan, Barbier, Jean
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Disordered Systems and Neural Networks Statistical Mechanics Information Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Optimal generalisation and learning transition in extensive-width shallow neural networks near interpolation
by: Barbier, Jean, et al.
Published: (2025)

Statistical mechanics of extensive-width Bayesian neural networks near interpolation
by: Barbier, Jean, et al.
Published: (2025)

Statistical physics of deep learning: Optimal learning of a multi-layer perceptron near interpolation
by: Barbier, Jean, et al.
Published: (2025)

Microscopic and collective signatures of feature learning in neural networks
by: Corti, Andrea, et al.
Published: (2025)

Compressed sensing with l0-norm: statistical physics analysis and algorithms for signal recovery
by: Barbier, D., et al.
Published: (2023)

Matrix denoising: Bayes-optimal estimators via low-degree polynomials
by: Semerjian, Guilhem
Published: (2024)

When low-loss paths make a binary neuron trainable: detecting algorithmic transitions with the connected ensemble
by: Barbier, Damien
Published: (2026)

Finding the right path: statistical mechanics of connected solutions in constraint satisfaction problems
by: Barbier, Damien
Published: (2025)

Spring-block theory of feature learning in deep neural networks
by: Shi, Cheng, et al.
Published: (2024)

Replica Analysis for Ensemble Techniques in Variable Selection
by: Takahashi, Takashi
Published: (2024)

The committee machine: Computational to statistical gaps in learning a two-layers neural network
by: Aubin, Benjamin, et al.
Published: (2018)

Geometry and universal scaling of Pareto-optimal signal compression
by: Berx, Jonas
Published: (2025)

On the role of non-linear latent features in bipartite generative neural networks
by: Bonnaire, Tony, et al.
Published: (2025)

Banded non-Hermitian random matrices, neural networks, and eigenvalue degeneracies
by: Huang, Richard, et al.
Published: (2026)

Competing nonlinearities, criticality, and order-to-chaos transition in deep networks
by: Lesser, Omri, et al.
Published: (2026)

Information-theoretic reduction of deep neural networks to linear models in the overparametrized proportional regime
by: Camilli, Francesco, et al.
Published: (2025)

Bayes-optimal learning of an extensive-width neural network from quadratically many samples
by: Maillard, Antoine, et al.
Published: (2024)

Phase probabilities in first-order transitions using machine learning
by: Sukhoverkhova, Diana, et al.
Published: (2024)

Some observations on the ambivalent role of symmetries in Bayesian inference problems
by: Semerjian, Guilhem
Published: (2025)

Spectral properties, localization transition and multifractal eigenvectors of the Laplacian on heterogeneous networks
by: da Silva, Jeferson D., et al.
Published: (2024)

Synaptic plasticity alters the nature of chaos transition in neural networks
by: Du, Wenkang, et al.
Published: (2024)

Tree networks of real-world data: analysis of efficiency and spatiotemporal scales
by: Cipollini, Davide, et al.
Published: (2024)

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

Information content in continuous attractor neural networks is preserved in the presence of moderate disordered background connectivity
by: Kühn, Tobias, et al.
Published: (2023)

How to escape atypical regions in the symmetric binary perceptron: a journey through connected-solutions states
by: Barbier, Damien
Published: (2024)

Statistical mechanics of transfer learning in fully-connected networks in the proportional limit
by: Ingrosso, Alessandro, et al.
Published: (2024)

Application of deep neural networks for computing the renormalization group flow of the two-dimensional phi^4 field theory
by: Zhao, Yueqi, et al.
Published: (2025)

Predictive power of a Bayesian effective action for fully-connected one hidden layer neural networks in the proportional limit
by: Baglioni, P., et al.
Published: (2024)

Sampling the space of solutions of an artificial neural network
by: Zambon, Alessandro, et al.
Published: (2025)

Machine learning analysis of dimensional reduction conjecture for nonequilibrium Berezinskii-Kosterlitz-Thouless transition in three dimensions
by: Haga, Taiki
Published: (2023)

Manageable to unmanageable transition in a fractal model of project networks
by: Vazquez, Alexei
Published: (2023)

Explosive neural networks via higher-order interactions in curved statistical manifolds
by: Aguilera, Miguel, et al.
Published: (2024)

Preferential attachment and power-law degree distributions in heterogeneous multilayer hypergraphs
by: Di Lauro, Francesco, et al.
Published: (2025)

Discontinuous BBP transitions
by: Bocchi, Dario, et al.
Published: (2026)

The dynamics of neural codes in biological and artificial neural networks
by: Morales, Guillermo B.
Published: (2024)

A Physical Theory of Two-stage Thermalization
by: Jonay, Cheryne, et al.
Published: (2023)

Graphical model for factorization and completion of relatively high rank tensors by sparse sampling
by: Cavaliere, Angelo Giorgio, et al.
Published: (2025)

Random-Energy Secret Sharing via Extreme Synergy
by: Ngampruetikorn, Vudtiwat, et al.
Published: (2023)

Power-law banded random matrix ensemble as a model for quantum many-body Hamiltonians
by: Buijsman, Wouter, et al.
Published: (2025)

Evidence that the AT transition disappears below six dimensions
by: Vedula, Bharadwaj, et al.
Published: (2024)