Monitoring for a Phase Transition in a Time Series of Wigner Matrices

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Dörnemann, Nina, Kokoszka, Piotr, Kutta, Tim, Lee, Sunmin
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911042477490176
author Dörnemann, Nina
Kokoszka, Piotr
Kutta, Tim
Lee, Sunmin
author_facet Dörnemann, Nina
Kokoszka, Piotr
Kutta, Tim
Lee, Sunmin
contents We develop methodology and theory for the detection of a phase transition in a time-series of high-dimensional random matrices. In the model we study, at each time point \( t = 1,2,\ldots \), we observe a deformed Wigner matrix \( \mathbf{M}_t \), where the unobservable deformation represents a latent signal. This signal is detectable only in the supercritical regime, and our objective is to detect the transition to this regime in real time, as new matrix--valued observations arrive. Our approach is based on a partial sum process of extremal eigenvalues of $\mathbf{M}_t$, and its theoretical analysis combines state-of-the-art tools from random-matrix-theory and Gaussian approximations. The resulting detector is self-normalized, which ensures appropriate scaling for convergence and a pivotal limit, without any additional parameter estimation. Simulations show excellent performance for varying dimensions. Applications to pollution monitoring and social interactions in primates illustrate the usefulness of our approach.
format Preprint
id arxiv_https___arxiv_org_abs_2507_04983
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Monitoring for a Phase Transition in a Time Series of Wigner Matrices
Dörnemann, Nina
Kokoszka, Piotr
Kutta, Tim
Lee, Sunmin
Statistics Theory
Probability
We develop methodology and theory for the detection of a phase transition in a time-series of high-dimensional random matrices. In the model we study, at each time point \( t = 1,2,\ldots \), we observe a deformed Wigner matrix \( \mathbf{M}_t \), where the unobservable deformation represents a latent signal. This signal is detectable only in the supercritical regime, and our objective is to detect the transition to this regime in real time, as new matrix--valued observations arrive. Our approach is based on a partial sum process of extremal eigenvalues of $\mathbf{M}_t$, and its theoretical analysis combines state-of-the-art tools from random-matrix-theory and Gaussian approximations. The resulting detector is self-normalized, which ensures appropriate scaling for convergence and a pivotal limit, without any additional parameter estimation. Simulations show excellent performance for varying dimensions. Applications to pollution monitoring and social interactions in primates illustrate the usefulness of our approach.
title Monitoring for a Phase Transition in a Time Series of Wigner Matrices
topic Statistics Theory
Probability
url https://arxiv.org/abs/2507.04983