Robust random graph matching in Gaussian models via vector approximate message passing

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autore principale: Li, Zhangsong
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910974555979776
author Li, Zhangsong
author_facet Li, Zhangsong
contents In this paper, we focus on the matching recovery problem between a pair of correlated Gaussian Wigner matrices with a latent vertex correspondence. We are particularly interested in a robust version of this problem such that our observation is a perturbed input $(A+E,B+F)$ where $(A,B)$ is a pair of correlated Gaussian Wigner matrices and $E,F$ are adversarially chosen matrices supported on an unknown $εn * εn$ principle minor of $A,B$, respectively. We propose a vector approximate message passing (vector AMP) algorithm that succeeds in polynomial time as long as the correlation $ρ$ between $(A,B)$ is a non-vanishing constant and $ε= o\big( \tfrac{1}{(\log n)^{20}} \big)$. The main methodological inputs for our result are the iterative random graph matching algorithm proposed in \cite{DL22+, DL23+} and the spectral cleaning procedure proposed in \cite{IS24+}. To the best of our knowledge, our algorithm is the first efficient random graph matching type algorithm that is robust under any adversarial perturbations of $n^{1-o(1)}$ size.
format Preprint
id arxiv_https___arxiv_org_abs_2412_16457
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Robust random graph matching in Gaussian models via vector approximate message passing
Li, Zhangsong
Machine Learning
Data Structures and Algorithms
Probability
Statistics Theory
68Q87, 90C35
In this paper, we focus on the matching recovery problem between a pair of correlated Gaussian Wigner matrices with a latent vertex correspondence. We are particularly interested in a robust version of this problem such that our observation is a perturbed input $(A+E,B+F)$ where $(A,B)$ is a pair of correlated Gaussian Wigner matrices and $E,F$ are adversarially chosen matrices supported on an unknown $εn * εn$ principle minor of $A,B$, respectively. We propose a vector approximate message passing (vector AMP) algorithm that succeeds in polynomial time as long as the correlation $ρ$ between $(A,B)$ is a non-vanishing constant and $ε= o\big( \tfrac{1}{(\log n)^{20}} \big)$. The main methodological inputs for our result are the iterative random graph matching algorithm proposed in \cite{DL22+, DL23+} and the spectral cleaning procedure proposed in \cite{IS24+}. To the best of our knowledge, our algorithm is the first efficient random graph matching type algorithm that is robust under any adversarial perturbations of $n^{1-o(1)}$ size.
title Robust random graph matching in Gaussian models via vector approximate message passing
topic Machine Learning
Data Structures and Algorithms
Probability
Statistics Theory
68Q87, 90C35
url https://arxiv.org/abs/2412.16457