Saved in:
Bibliographic Details
Main Authors: Erazo, Cristopher, Acevedo, Santiago, Ingrosso, Alessandro
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.17427
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914277608128512
author Erazo, Cristopher
Acevedo, Santiago
Ingrosso, Alessandro
author_facet Erazo, Cristopher
Acevedo, Santiago
Ingrosso, Alessandro
contents We use the Binary Intrinsic Dimension (BID), a geometrical measure designed for binary data, to analyze the Hopfield model, a paradigmatic spin system from statistical mechanics, machine learning and neuroscience. The BID allows us to characterize the phases and transitions of this system, and moreover it is robust against finite-size effects that interfere with the correct numerical estimation of the spin-glass order parameter ($q$). We observe that the BID scales linearly with system size in the retrieval and paramagnetic phases, where the correlations between spins are small, and exhibits sublinear scaling in the whole spin-glass phase, highlighting its correlated structure. Furthermore, we establish a direct relationship between the BID and the overlap distribution, unveiling a novel connection between the geometry of the state-space and standard spin order parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2601_17427
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle The dimensionality of the Hopfield model
Erazo, Cristopher
Acevedo, Santiago
Ingrosso, Alessandro
Disordered Systems and Neural Networks
Computational Physics
We use the Binary Intrinsic Dimension (BID), a geometrical measure designed for binary data, to analyze the Hopfield model, a paradigmatic spin system from statistical mechanics, machine learning and neuroscience. The BID allows us to characterize the phases and transitions of this system, and moreover it is robust against finite-size effects that interfere with the correct numerical estimation of the spin-glass order parameter ($q$). We observe that the BID scales linearly with system size in the retrieval and paramagnetic phases, where the correlations between spins are small, and exhibits sublinear scaling in the whole spin-glass phase, highlighting its correlated structure. Furthermore, we establish a direct relationship between the BID and the overlap distribution, unveiling a novel connection between the geometry of the state-space and standard spin order parameters.
title The dimensionality of the Hopfield model
topic Disordered Systems and Neural Networks
Computational Physics
url https://arxiv.org/abs/2601.17427