Cover Image

High-dimensional manifold of solutions in neural networks: insights from statistical physics

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Malatesta, Enrico M.
Format:	Preprint
Published:	2023
Subjects:	Disordered Systems and Neural Networks Machine Learning Probability Statistics Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The twin peaks of learning neural networks
by: Demyanenko, Elizaveta, et al.
Published: (2024)

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

Generalization performance of narrow one-hidden layer networks in the teacher-student setting
by: Ortiz, Rodrigo Pérez, et al.
Published: (2025)

Exact full-RSB SAT/UNSAT transition in infinitely wide two-layer neural networks
by: Annesi, Brandon L., et al.
Published: (2024)

A Fourier perspective on the learning dynamics of neural networks: from sample complexities to mechanistic insights
by: Ricci, Fabiola, et al.
Published: (2026)

Properties of the geometry of solutions and capacity of multi-layer neural networks with Rectified Linear Units activations
by: Baldassi, Carlo, et al.
Published: (2019)

Gaussian mixtures and non-parametric likelihoods through the lens of statistical mechanics
by: Ghosh, Subhroshekhar, et al.
Published: (2026)

Injectivity of ReLU networks: perspectives from statistical physics
by: Maillard, Antoine, et al.
Published: (2023)

Precise asymptotic analysis of Sobolev training for random feature models
by: Fisher, Katharine E, et al.
Published: (2025)

Gaussian Universality of Perceptrons with Random Labels
by: Gerace, Federica, et al.
Published: (2022)

Spectral Phase Transition and Optimal PCA in Block-Structured Spiked models
by: Mergny, Pierre, et al.
Published: (2024)

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

Fixed width treelike neural networks capacity analysis -- generic activations
by: Stojnic, Mihailo
Published: (2024)

Analysis of Diffusion Models for Manifold Data
by: George, Anand Jerry, et al.
Published: (2025)

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

Exact capacity of the \emph{wide} hidden layer treelike neural networks with generic activations
by: Stojnic, Mihailo
Published: (2024)

Structure of solutions to continuous constraint satisfaction problems through the statistics of wedged and inscribed spheres
by: Kent-Dobias, Jaron
Published: (2025)

High-dimensional robust regression under heavy-tailed data: Asymptotics and Universality
by: Adomaityte, Urte, et al.
Published: (2023)

Leveraging chaotic transients in the training of artificial neural networks
by: Jiménez-González, Pedro, et al.
Published: (2025)

Dynamical stability and chaos in artificial neural network trajectories along training
by: Danovski, Kaloyan, et al.
Published: (2024)

A Friendly Tutorial on Mean-Field Spin Glass Techniques for Non-Physicists
by: Montanari, Andrea, et al.
Published: (2022)

Low-rank Matrix Estimation with Inhomogeneous Noise
by: Guionnet, Alice, et al.
Published: (2022)

Feature learning from non-Gaussian inputs: the case of Independent Component Analysis in high dimensions
by: Ricci, Fabiola, et al.
Published: (2025)

The Role of Pseudo-labels in Self-training Linear Classifiers on High-dimensional Gaussian Mixture Data
by: Takahashi, Takashi
Published: (2022)

Capacity of the Hebbian-Hopfield network associative memory
by: Stojnic, Mihailo
Published: (2024)

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

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

Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks
by: Nguyen, Minh-Toan, et al.
Published: (2026)

A spin-glass model for the loss surfaces of generative adversarial networks
by: Baskerville, Nicholas P, et al.
Published: (2021)

Classification of Heavy-tailed Features in High Dimensions: a Superstatistical Approach
by: Adomaityte, Urte, et al.
Published: (2023)

On the Geometry of Regularization in Adversarial Training: High-Dimensional Asymptotics and Generalization Bounds
by: Vilucchio, Matteo, et al.
Published: (2024)

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

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

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

Diffusive geodesics wandering in networks of rigid chains
by: Marquis, Ulysse
Published: (2025)

Drift-Diffusion Matching: Embedding dynamics in latent manifolds of asymmetric neural networks
by: Nartallo-Kaluarachchi, Ramón, et al.
Published: (2026)

Better Together: Cross and Joint Covariances Enhance Signal Detectability in Undersampled Data
by: Swain, Arabind, et al.
Published: (2025)

The unbearable lightness of Restricted Boltzmann Machines: Theoretical Insights and Biological Applications
by: di Sarra, Giovanni, et al.
Published: (2025)

Effective Method for Inverse Ising Problem under Missing Observations in Restricted Boltzmann Machines
by: Sekimoto, Kaiji, et al.
Published: (2025)

Lost in Retraining: Roaming the Parameter Space of Exponential Families Under Closed-Loop Learning
by: Jangjoo, Fariba, et al.
Published: (2025)