Copertina

Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Defilippis, Leonardo, Xu, Yizhou, Girardin, Julius, Troiani, Emanuele, Erba, Vittorio, Zdeborová, Lenka, Loureiro, Bruno, Krzakala, Florent
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Disordered Systems and Neural Networks Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Single-Head Attention in High Dimensions: A Theory of Generalization, Weights Spectra, and Scaling Laws
di: Boncoraglio, Fabrizio, et al.
Pubblicazione: (2025)

The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks
di: Erba, Vittorio, et al.
Pubblicazione: (2025)

Fundamental computational limits of weak learnability in high-dimensional multi-index models
di: Troiani, Emanuele, et al.
Pubblicazione: (2024)

Quenches in the Sherrington-Kirkpatrick model
di: Erba, Vittorio, et al.
Pubblicazione: (2024)

Statistical mechanics of the maximum-average submatrix problem
di: Erba, Vittorio, et al.
Pubblicazione: (2023)

Bayes optimal learning of attention-indexed models
di: Boncoraglio, Fabrizio, et al.
Pubblicazione: (2025)

Learning with Restricted Boltzmann Machines: Asymptotics of AMP and GD in High Dimensions
di: Xu, Yizhou, et al.
Pubblicazione: (2025)

Fundamental limits of learning in sequence multi-index models and deep attention networks: High-dimensional asymptotics and sharp thresholds
di: Troiani, Emanuele, et al.
Pubblicazione: (2025)

Bilinear Sequence Regression: A Model for Learning from Long Sequences of High-dimensional Tokens
di: Erba, Vittorio, et al.
Pubblicazione: (2024)

Asymptotics of SGD in Sequence-Single Index Models and Single-Layer Attention Networks
di: Arnaboldi, Luca, et al.
Pubblicazione: (2025)

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

Optimal Spectral Transitions in High-Dimensional Multi-Index Models
di: Defilippis, Leonardo, et al.
Pubblicazione: (2025)

Fundamental Limits of Matrix Sensing: Exact Asymptotics, Universality, and Applications
di: Xu, Yizhou, et al.
Pubblicazione: (2025)

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

Analysis of Bootstrap and Subsampling in High-dimensional Regularized Regression
di: Clarté, Lucas, et al.
Pubblicazione: (2024)

Computational Thresholds in Multi-Modal Learning via the Spiked Matrix-Tensor Model
di: Tabanelli, Hugo, et al.
Pubblicazione: (2025)

On the Atypical Solutions of the Symmetric Binary Perceptron
di: Barbier, Damien, et al.
Pubblicazione: (2023)

A solvable high-dimensional model where nonlinear autoencoders learn structure invisible to PCA while test loss misaligns with generalization
di: Mendes, Vicente Conde, et al.
Pubblicazione: (2026)

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

Sampling with flows, diffusion and autoregressive neural networks: A spin-glass perspective
di: Ghio, Davide, et al.
Pubblicazione: (2023)

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

The phase diagram of compressed sensing with $\ell_0$-norm regularization
di: Barbier, Damien, et al.
Pubblicazione: (2024)

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

The maximum-average subtensor problem: equilibrium and out-of-equilibrium properties
di: Erba, Vittorio, et al.
Pubblicazione: (2025)

On the existence of consistent adversarial attacks in high-dimensional linear classification
di: Vilucchio, Matteo, et al.
Pubblicazione: (2025)

A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-Offs
di: Tanner, Kasimir, et al.
Pubblicazione: (2024)

The Rules-and-Facts Model for Simultaneous Generalization and Memorization in Neural Networks
di: Farné, Gabriele, et al.
Pubblicazione: (2026)

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

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

High-dimensional Asymptotics of Denoising Autoencoders
di: Cui, Hugo, et al.
Pubblicazione: (2023)

Building Conformal Prediction Intervals with Approximate Message Passing
di: Clarté, Lucas, et al.
Pubblicazione: (2024)

Optimal thresholds and algorithms for a model of multi-modal learning in high dimensions
di: Keup, Christian, et al.
Pubblicazione: (2024)

Dynamical Cavity Method for Hypergraphs and its Application to Quenches in the k-XOR-SAT Problem
di: Maier, Aude, et al.
Pubblicazione: (2024)

Dynamical Phase Transitions in Graph Cellular Automata
di: Behrens, Freya, et al.
Pubblicazione: (2023)

Inference in Spreading Processes with Neural-Network Priors
di: Ghio, Davide, et al.
Pubblicazione: (2025)

Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning
di: Dandi, Yatin, et al.
Pubblicazione: (2026)

Minority Takeover in Majority Dynamics: Searching for Rare Initializations via the History Passing Algorithm
di: Jankola, Marek, et al.
Pubblicazione: (2025)

Spectral Thresholds in Correlated Spiked Models and Fundamental Limits of Partial Least Squares
di: Mergny, Pierre, et al.
Pubblicazione: (2025)

Counting and Hardness-of-Finding Fixed Points in Cellular Automata on Random Graphs
di: Koller, Cédric, et al.
Pubblicazione: (2024)

Rigorous Asymptotics for First-Order Algorithms Through the Dynamical Cavity Method
di: Dandi, Yatin, et al.
Pubblicazione: (2026)