Testing properties of trees in graphical models with covariance queries

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Burova, Sofiya, Calvillo, Francisco, Lugosi, Gábor, Zwiernik, Piotr
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914569356574720
author Burova, Sofiya
Calvillo, Francisco
Lugosi, Gábor
Zwiernik, Piotr
author_facet Burova, Sofiya
Calvillo, Francisco
Lugosi, Gábor
Zwiernik, Piotr
contents We consider the problem of testing properties of graphs underlying high-dimensional graphical models. We adopt the model of covariance queries introduced by Lugosi, Truszkowski, Velona, and Zwiernik (2021). We study the case when the underlying graph is a tree. The main results of the paper show that, while reconstructing the entire tree may be costly, certain global structural properties can be tested efficiently. In particular, we design randomized tests for global structural properties that use a sub-quadratic number of queries. We develop testing procedures for several fundamental properties, including the number of leaves, the maximum degree, the typical distance, and the diameter of the tree. For each property, we obtain explicit query complexity bounds that depend on the target threshold and tolerance parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2605_15996
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Testing properties of trees in graphical models with covariance queries
Burova, Sofiya
Calvillo, Francisco
Lugosi, Gábor
Zwiernik, Piotr
Machine Learning
Statistics Theory
We consider the problem of testing properties of graphs underlying high-dimensional graphical models. We adopt the model of covariance queries introduced by Lugosi, Truszkowski, Velona, and Zwiernik (2021). We study the case when the underlying graph is a tree. The main results of the paper show that, while reconstructing the entire tree may be costly, certain global structural properties can be tested efficiently. In particular, we design randomized tests for global structural properties that use a sub-quadratic number of queries. We develop testing procedures for several fundamental properties, including the number of leaves, the maximum degree, the typical distance, and the diameter of the tree. For each property, we obtain explicit query complexity bounds that depend on the target threshold and tolerance parameters.
title Testing properties of trees in graphical models with covariance queries
topic Machine Learning
Statistics Theory
url https://arxiv.org/abs/2605.15996