Nonparametric two-sample hypothesis testing for low-rank random graphs of differing sizes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Agterberg, Joshua, Tang, Minh, Priebe, Carey
Format: Preprint
Published: 2020
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918376486469632
author Agterberg, Joshua
Tang, Minh
Priebe, Carey
author_facet Agterberg, Joshua
Tang, Minh
Priebe, Carey
contents Given two networks of differing sizes, it is of interest to test whether the two networks belong to the same distribution. We formalize the notion of "equality of distribution" under the framework of the generalized random dot product graph, which considers as special cases a number of popular network models with low-rank expectations. We then propose a nonparametric two-sample test statistic to conduct this test, assuming only that the networks have independent edges generated from low-rank probability matrices. Our proposed test statistic involves using the maximum mean discrepancy applied to suitably rotated rows of a graph embedding, where the rotation is estimated using optimal transport. We show that our test statistic, appropriately scaled, is consistent for sufficiently dense graphs, and we study its convergence under different sparsity regimes, and our results are demonstrated in numerical simulations.
format Preprint
id arxiv_https___arxiv_org_abs_2012_09828
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Nonparametric two-sample hypothesis testing for low-rank random graphs of differing sizes
Agterberg, Joshua
Tang, Minh
Priebe, Carey
Statistics Theory
Given two networks of differing sizes, it is of interest to test whether the two networks belong to the same distribution. We formalize the notion of "equality of distribution" under the framework of the generalized random dot product graph, which considers as special cases a number of popular network models with low-rank expectations. We then propose a nonparametric two-sample test statistic to conduct this test, assuming only that the networks have independent edges generated from low-rank probability matrices. Our proposed test statistic involves using the maximum mean discrepancy applied to suitably rotated rows of a graph embedding, where the rotation is estimated using optimal transport. We show that our test statistic, appropriately scaled, is consistent for sufficiently dense graphs, and we study its convergence under different sparsity regimes, and our results are demonstrated in numerical simulations.
title Nonparametric two-sample hypothesis testing for low-rank random graphs of differing sizes
topic Statistics Theory
url https://arxiv.org/abs/2012.09828