Learning the Intrinsic Dimensionality of Fermi-Pasta-Ulam-Tsingou Trajectories: A Nonlinear Approach using a Deep Autoencoder Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Marchetti, Gionni
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914403958390784
author Marchetti, Gionni
author_facet Marchetti, Gionni
contents We address the intrinsic dimensionality (ID) of high-dimensional trajectories, comprising $n_s = 4\,000\,000$ data points, of the Fermi-Pasta-Ulam-Tsingou (FPUT) $β$ model with $N = 32$ oscillators. To this end, a deep autoencoder (DAE) is used to infer the ID in the weakly nonlinear regime where energy recurrences are observed ($β\lesssim 1$). We find that the trajectories lie on a nonlinear Riemannian manifold of dimension $m^{\ast} = 2$ embedded in a $64$-dimensional phase space. By contrast, principal component analysis (PCA) together with the Participation Ratio (PR) method provides only a reasonable upper bound on the ID for each value of $β$. Our DAE further reveals that the ID increases to $m^{\ast} = 3$ at $β= 1.1$, coinciding with a symmetry-breaking (SB) phenomenon characteristic of the $β$ model, in which additional energy modes with even wave numbers $k = 2, 4$ become excited. Notably, the SB phenomenon cannot be detected by the linear approach provided by PCA.
format Preprint
id arxiv_https___arxiv_org_abs_2601_19567
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning the Intrinsic Dimensionality of Fermi-Pasta-Ulam-Tsingou Trajectories: A Nonlinear Approach using a Deep Autoencoder Model
Marchetti, Gionni
Statistical Mechanics
Machine Learning
We address the intrinsic dimensionality (ID) of high-dimensional trajectories, comprising $n_s = 4\,000\,000$ data points, of the Fermi-Pasta-Ulam-Tsingou (FPUT) $β$ model with $N = 32$ oscillators. To this end, a deep autoencoder (DAE) is used to infer the ID in the weakly nonlinear regime where energy recurrences are observed ($β\lesssim 1$). We find that the trajectories lie on a nonlinear Riemannian manifold of dimension $m^{\ast} = 2$ embedded in a $64$-dimensional phase space. By contrast, principal component analysis (PCA) together with the Participation Ratio (PR) method provides only a reasonable upper bound on the ID for each value of $β$. Our DAE further reveals that the ID increases to $m^{\ast} = 3$ at $β= 1.1$, coinciding with a symmetry-breaking (SB) phenomenon characteristic of the $β$ model, in which additional energy modes with even wave numbers $k = 2, 4$ become excited. Notably, the SB phenomenon cannot be detected by the linear approach provided by PCA.
title Learning the Intrinsic Dimensionality of Fermi-Pasta-Ulam-Tsingou Trajectories: A Nonlinear Approach using a Deep Autoencoder Model
topic Statistical Mechanics
Machine Learning
url https://arxiv.org/abs/2601.19567