Overparametrization bends the landscape: BBP transitions at initialization in simple Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Annesi, Brandon Livio, Bocchi, Dario, Cammarota, Chiara
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915566536622080
author Annesi, Brandon Livio
Bocchi, Dario
Cammarota, Chiara
author_facet Annesi, Brandon Livio
Bocchi, Dario
Cammarota, Chiara
contents High-dimensional non-convex loss landscapes play a central role in the theory of Machine Learning. Gaining insight into how these landscapes interact with gradient-based optimization methods, even in relatively simple models, can shed light on this enigmatic feature of neural networks. In this work, we will focus on a prototypical simple learning problem, which generalizes the Phase Retrieval inference problem by allowing the exploration of overparametrized settings. Using techniques from field theory, we analyze the spectrum of the Hessian at initialization and identify a Baik-Ben Arous-Péché (BBP) transition in the amount of data that separates regimes where the initialization is informative or uninformative about a planted signal of a teacher-student setup. Crucially, we demonstrate how overparameterization can bend the loss landscape, shifting the transition point, even reaching the information-theoretic weak-recovery threshold in the large overparameterization limit, while also altering its qualitative nature. We distinguish between continuous and discontinuous BBP transitions and support our analytical predictions with simulations, examining how they compare to the finite-N behavior. In the case of discontinuous BBP transitions strong finite-N corrections allow the retrieval of information at a signal-to-noise ratio (SNR) smaller than the predicted BBP transition. In these cases we provide estimates for a new lower SNR threshold that marks the point at which initialization becomes entirely uninformative.
format Preprint
id arxiv_https___arxiv_org_abs_2510_18435
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Overparametrization bends the landscape: BBP transitions at initialization in simple Neural Networks
Annesi, Brandon Livio
Bocchi, Dario
Cammarota, Chiara
Disordered Systems and Neural Networks
Statistical Mechanics
Spectral Theory
Machine Learning
High-dimensional non-convex loss landscapes play a central role in the theory of Machine Learning. Gaining insight into how these landscapes interact with gradient-based optimization methods, even in relatively simple models, can shed light on this enigmatic feature of neural networks. In this work, we will focus on a prototypical simple learning problem, which generalizes the Phase Retrieval inference problem by allowing the exploration of overparametrized settings. Using techniques from field theory, we analyze the spectrum of the Hessian at initialization and identify a Baik-Ben Arous-Péché (BBP) transition in the amount of data that separates regimes where the initialization is informative or uninformative about a planted signal of a teacher-student setup. Crucially, we demonstrate how overparameterization can bend the loss landscape, shifting the transition point, even reaching the information-theoretic weak-recovery threshold in the large overparameterization limit, while also altering its qualitative nature. We distinguish between continuous and discontinuous BBP transitions and support our analytical predictions with simulations, examining how they compare to the finite-N behavior. In the case of discontinuous BBP transitions strong finite-N corrections allow the retrieval of information at a signal-to-noise ratio (SNR) smaller than the predicted BBP transition. In these cases we provide estimates for a new lower SNR threshold that marks the point at which initialization becomes entirely uninformative.
title Overparametrization bends the landscape: BBP transitions at initialization in simple Neural Networks
topic Disordered Systems and Neural Networks
Statistical Mechanics
Spectral Theory
Machine Learning
url https://arxiv.org/abs/2510.18435