Guardado en:
Detalles Bibliográficos
Autores principales: Defilippis, Leonardo, Krzakala, Florent, Loureiro, Bruno, Maillard, Antoine
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2602.05846
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915778202173440
author Defilippis, Leonardo
Krzakala, Florent
Loureiro, Bruno
Maillard, Antoine
author_facet Defilippis, Leonardo
Krzakala, Florent
Loureiro, Bruno
Maillard, Antoine
contents In this work, we provide a sharp theory of scaling laws for two-layer neural networks trained on a class of hierarchical multi-index targets, in a genuinely representation-limited regime. We derive exact information-theoretic scaling laws for subspace recovery and prediction error, revealing how the hierarchical features of the target are sequentially learned through a cascade of phase transitions. We further show that these optimal rates are achieved by a simple, target-agnostic spectral estimator, which can be interpreted as the small learning-rate limit of gradient descent on the first-layer weights. Once an adapted representation is identified, the readout can be learned statistically optimally, using an efficient procedure. As a consequence, we provide a unified and rigorous explanation of scaling laws, plateau phenomena, and spectral structure in shallow neural networks trained on such hierarchical targets.
format Preprint
id arxiv_https___arxiv_org_abs_2602_05846
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Optimal scaling laws in learning hierarchical multi-index models
Defilippis, Leonardo
Krzakala, Florent
Loureiro, Bruno
Maillard, Antoine
Machine Learning
In this work, we provide a sharp theory of scaling laws for two-layer neural networks trained on a class of hierarchical multi-index targets, in a genuinely representation-limited regime. We derive exact information-theoretic scaling laws for subspace recovery and prediction error, revealing how the hierarchical features of the target are sequentially learned through a cascade of phase transitions. We further show that these optimal rates are achieved by a simple, target-agnostic spectral estimator, which can be interpreted as the small learning-rate limit of gradient descent on the first-layer weights. Once an adapted representation is identified, the readout can be learned statistically optimally, using an efficient procedure. As a consequence, we provide a unified and rigorous explanation of scaling laws, plateau phenomena, and spectral structure in shallow neural networks trained on such hierarchical targets.
title Optimal scaling laws in learning hierarchical multi-index models
topic Machine Learning
url https://arxiv.org/abs/2602.05846