Joint learning of a network of linear dynamical systems via total variation penalization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Donnat, Claire, Klopp, Olga, Tyagi, Hemant
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908783069888512
author Donnat, Claire
Klopp, Olga
Tyagi, Hemant
author_facet Donnat, Claire
Klopp, Olga
Tyagi, Hemant
contents We consider the problem of joint estimation of the parameters of $m$ linear dynamical systems, given access to single realizations of their respective trajectories, each of length $T$. The linear systems are assumed to reside on the nodes of an undirected and connected graph $G = ([m], \mathcal{E})$, and the system matrices are assumed to either vary smoothly or exhibit small number of ``jumps'' across the edges. We consider a total variation penalized least-squares estimator and derive non-asymptotic bounds on the mean squared error (MSE) which hold with high probability. In particular, the bounds imply for certain choices of well connected $G$ that the MSE goes to zero as $m$ increases, even when $T$ is constant. The theoretical results are supported by extensive experiments on synthetic and real data.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18737
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Joint learning of a network of linear dynamical systems via total variation penalization
Donnat, Claire
Klopp, Olga
Tyagi, Hemant
Statistics Theory
Optimization and Control
Machine Learning
We consider the problem of joint estimation of the parameters of $m$ linear dynamical systems, given access to single realizations of their respective trajectories, each of length $T$. The linear systems are assumed to reside on the nodes of an undirected and connected graph $G = ([m], \mathcal{E})$, and the system matrices are assumed to either vary smoothly or exhibit small number of ``jumps'' across the edges. We consider a total variation penalized least-squares estimator and derive non-asymptotic bounds on the mean squared error (MSE) which hold with high probability. In particular, the bounds imply for certain choices of well connected $G$ that the MSE goes to zero as $m$ increases, even when $T$ is constant. The theoretical results are supported by extensive experiments on synthetic and real data.
title Joint learning of a network of linear dynamical systems via total variation penalization
topic Statistics Theory
Optimization and Control
Machine Learning
url https://arxiv.org/abs/2511.18737