跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2511.11927 · v3

Sparse corruption in low-rank matrix inference: the PCA benchmark

首次提交 2025-11-15 07:09
版本更新 2026-11-20 00:09
雷达观测 2026-11-20 14:52
arXiv ↗PDF ↗

摘要

Principal Component Analysis (PCA) is a standard tool for extracting a low-rank signal from noisy observations. It is known that when applying PCA to a rank-one signal corrupted by a dense, homogeneous noise, in the large matrix size limit, the BBP transition occurs, where the emergence of an outlying eigenvalue and the alignment of the corresponding eigenvector occur at the same critical signal strength. Here we study the case of sparse noise corruption. The noise matrix is modelled as the adjacency matrix of a weighted undirected graph with finite average connectivity. Using the replica method, we analytically compute the typical top eigenvalue, the top eigenvector component density, and the overlap with the signal, through recursive distributional equations solved by population dynamics. We identify two signal-strength transitions as functions of graph connectivity: θcritθ_{\rm crit}, marking signal recovery by the top eigenvector and generalising the BBP transition, and θbθ_{\rm b}, where the signal-related eigenvalue detaches from the bulk. For noise with nonzero mean, these transitions need not coincide because of a structural sparse-graph outlier, leading to a discontinuous transition in the overlap with the top eigenvector. For a Random Regular degree distribution, we obtain exact closed-form expressions for both thresholds, the signal eigenvalue and the squared overlap, and show that the same formulas also predict the overlap of the signal with the second eigenvector in the intermediate regime θb<θ≤θcritθ_{\rm b}<θ\leq θ_{\rm crit}. For a Poissonian degree distribution, an approximate closure of the recursions yields fast and accurate predictions in the recovery phase that agree with exact results from population dynamics. We also recover dense-noise results in the large-connectivity limit, and validate the theory by numerical diagonalisation of large matrices.

作者备注:25 pages, 8 figures. Order of presentation of special cases flipped, approximation for the Poisson case made explicit (App B), quality of said approximation quantified in App C, typos fixed

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v3,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v3 · 2026-11-20 00:09 · 最新观测版本

Sparse corruption in low-rank matrix inference: the PCA benchmark

Principal Component Analysis (PCA) is a standard tool for extracting a low-rank signal from noisy observations. It is known that when applying PCA to a rank-one signal corrupted by a dense, homogeneous noise, in the large matrix size limit, the BBP transition occurs, where the emergence of an outlying eigenvalue and the alignment of the corresponding eigenvector occur at the same critical signal strength. Here we study the case of sparse noise corruption. The noise matrix is modelled as the adjacency matrix of a weighted undirected graph with finite average connectivity. Using the replica method, we analytically compute the typical top eigenvalue, the top eigenvector component density, and the overlap with the signal, through recursive distributional equations solved by population dynamics. We identify two signal-strength transitions as functions of graph connectivity: θcritθ_{\rm crit}, marking signal recovery by the top eigenvector and generalising the BBP transition, and θbθ_{\rm b}, where the signal-related eigenvalue detaches from the bulk. For noise with nonzero mean, these transitions need not coincide because of a structural sparse-graph outlier, leading to a discontinuous transition in the overlap with the top eigenvector. For a Random Regular degree distribution, we obtain exact closed-form expressions for both thresholds, the signal eigenvalue and the squared overlap, and show that the same formulas also predict the overlap of the signal with the second eigenvector in the intermediate regime θb<θ≤θcritθ_{\rm b}<θ\leq θ_{\rm crit}. For a Poissonian degree distribution, an approximate closure of the recursions yields fast and accurate predictions in the recovery phase that agree with exact results from population dynamics. We also recover dense-noise results in the large-connectivity limit, and validate the theory by numerical diagonalisation of large matrices.

查看此版本解读 →查看此版本原文 ↗