Orthogonal Approximate Message Passing with Optimal Spectral Initializations for Rectangular Spiked Matrix Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Haohua, Liu, Songbin, Ma, Junjie
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914214340198400
author Chen, Haohua
Liu, Songbin
Ma, Junjie
author_facet Chen, Haohua
Liu, Songbin
Ma, Junjie
contents We propose an orthogonal approximate message passing (OAMP) algorithm for signal estimation in the rectangular spiked matrix model with general rotationally invariant (RI) noise. We establish a rigorous state evolution that precisely characterizes the algorithm's high-dimensional dynamics and enables the construction of iteration-wise optimal denoisers. Within this framework, we accommodate spectral initializations under minimal assumptions on the empirical noise spectrum. In the rectangular setting, where a single rank-one component typically generates multiple informative outliers, we further propose a procedure for combining these outliers under mild non-Gaussian signal assumptions. For general RI noise models, the predicted performance of the proposed optimal OAMP algorithm agrees with replica-symmetric predictions for the associated Bayes-optimal estimator, and we conjecture that it is statistically optimal within a broad class of iterative estimation methods.
format Preprint
id arxiv_https___arxiv_org_abs_2512_19334
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Orthogonal Approximate Message Passing with Optimal Spectral Initializations for Rectangular Spiked Matrix Models
Chen, Haohua
Liu, Songbin
Ma, Junjie
Information Theory
Machine Learning
Statistics Theory
We propose an orthogonal approximate message passing (OAMP) algorithm for signal estimation in the rectangular spiked matrix model with general rotationally invariant (RI) noise. We establish a rigorous state evolution that precisely characterizes the algorithm's high-dimensional dynamics and enables the construction of iteration-wise optimal denoisers. Within this framework, we accommodate spectral initializations under minimal assumptions on the empirical noise spectrum. In the rectangular setting, where a single rank-one component typically generates multiple informative outliers, we further propose a procedure for combining these outliers under mild non-Gaussian signal assumptions. For general RI noise models, the predicted performance of the proposed optimal OAMP algorithm agrees with replica-symmetric predictions for the associated Bayes-optimal estimator, and we conjecture that it is statistically optimal within a broad class of iterative estimation methods.
title Orthogonal Approximate Message Passing with Optimal Spectral Initializations for Rectangular Spiked Matrix Models
topic Information Theory
Machine Learning
Statistics Theory
url https://arxiv.org/abs/2512.19334