Structural Identifiability of Graphical Continuous Lyapunov Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Améndola, Carlos, Boege, Tobias, Hollering, Benjamin, Misra, Pratik
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915535231385600
author Améndola, Carlos
Boege, Tobias
Hollering, Benjamin
Misra, Pratik
author_facet Améndola, Carlos
Boege, Tobias
Hollering, Benjamin
Misra, Pratik
contents We prove two characterizations of model equivalence of acyclic graphical continuous Lyapunov models (GCLMs) with uncorrelated noise. The first result shows that two graphs are model equivalent if and only if they have the same skeleton and equivalent induced 4-node subgraphs. We also give a transformational characterization via structured edge reversals. The two theorems are Lyapunov analogues of celebrated results for Bayesian networks by Verma and Pearl, and Chickering, respectively. Our results have broad consequences for the theory of causal inference of GCLMs. First, we find that model equivalence classes of acyclic GCLMs refine the corresponding classes of Bayesian networks. Furthermore, we obtain polynomial-time algorithms to test model equivalence and structural identifiability of given directed acyclic graphs.
format Preprint
id arxiv_https___arxiv_org_abs_2510_04985
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Structural Identifiability of Graphical Continuous Lyapunov Models
Améndola, Carlos
Boege, Tobias
Hollering, Benjamin
Misra, Pratik
Statistics Theory
62H22, 60J60 (Primary) 15A24, 62R01, 60J70 (Secondary)
We prove two characterizations of model equivalence of acyclic graphical continuous Lyapunov models (GCLMs) with uncorrelated noise. The first result shows that two graphs are model equivalent if and only if they have the same skeleton and equivalent induced 4-node subgraphs. We also give a transformational characterization via structured edge reversals. The two theorems are Lyapunov analogues of celebrated results for Bayesian networks by Verma and Pearl, and Chickering, respectively. Our results have broad consequences for the theory of causal inference of GCLMs. First, we find that model equivalence classes of acyclic GCLMs refine the corresponding classes of Bayesian networks. Furthermore, we obtain polynomial-time algorithms to test model equivalence and structural identifiability of given directed acyclic graphs.
title Structural Identifiability of Graphical Continuous Lyapunov Models
topic Statistics Theory
62H22, 60J60 (Primary) 15A24, 62R01, 60J70 (Secondary)
url https://arxiv.org/abs/2510.04985