The Role of Rank in Mismatched Low-Rank Symmetric Matrix Estimation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Niu, Panpan, Liu, Yuhao, Fu, Teng, Fan, Jie, Deng, Chaowen, Huang, Zhongyi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915393081180160
author Niu, Panpan
Liu, Yuhao
Fu, Teng
Fan, Jie
Deng, Chaowen
Huang, Zhongyi
author_facet Niu, Panpan
Liu, Yuhao
Fu, Teng
Fan, Jie
Deng, Chaowen
Huang, Zhongyi
contents We investigate the performance of a Bayesian statistician tasked with recovering a rank-\(k\) signal matrix \(\bS \bS^{\top} \in \mathbb{R}^{n \times n}\), corrupted by element-wise additive Gaussian noise. This problem lies at the core of numerous applications in machine learning, signal processing, and statistics. We derive an analytic expression for the asymptotic mean-square error (MSE) of the Bayesian estimator under mismatches in the assumed signal rank, signal power, and signal-to-noise ratio (SNR), considering both sphere and Gaussian signals. Additionally, we conduct a rigorous analysis of how rank mismatch influences the asymptotic MSE. Our primary technical tools include the spectrum of Gaussian orthogonal ensembles (GOE) with low-rank perturbations and asymptotic behavior of \(k\)-dimensional spherical integrals.
format Preprint
id arxiv_https___arxiv_org_abs_2507_12019
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Role of Rank in Mismatched Low-Rank Symmetric Matrix Estimation
Niu, Panpan
Liu, Yuhao
Fu, Teng
Fan, Jie
Deng, Chaowen
Huang, Zhongyi
Information Theory
Signal Processing
We investigate the performance of a Bayesian statistician tasked with recovering a rank-\(k\) signal matrix \(\bS \bS^{\top} \in \mathbb{R}^{n \times n}\), corrupted by element-wise additive Gaussian noise. This problem lies at the core of numerous applications in machine learning, signal processing, and statistics. We derive an analytic expression for the asymptotic mean-square error (MSE) of the Bayesian estimator under mismatches in the assumed signal rank, signal power, and signal-to-noise ratio (SNR), considering both sphere and Gaussian signals. Additionally, we conduct a rigorous analysis of how rank mismatch influences the asymptotic MSE. Our primary technical tools include the spectrum of Gaussian orthogonal ensembles (GOE) with low-rank perturbations and asymptotic behavior of \(k\)-dimensional spherical integrals.
title The Role of Rank in Mismatched Low-Rank Symmetric Matrix Estimation
topic Information Theory
Signal Processing
url https://arxiv.org/abs/2507.12019