Nonnegative Low-rank Matrix Recovery Can Have Spurious Local Minima

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteur principal: Zhang, Richard Y.
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911389910564864
author Zhang, Richard Y.
author_facet Zhang, Richard Y.
contents Low-rank matrix recovery is well-known to exhibit benign nonconvexity under the restricted isometry property (RIP): every second-order critical point is globally optimal, so local methods provably recover the ground truth. Motivated by the strong empirical performance of projected gradient methods for nonnegative low-rank recovery problems, we investigate whether this benign geometry persists when the factor matrices are constrained to be elementwise nonnegative. In the simple setting of a rank-1 nonnegative ground truth, we confirm that benign nonconvexity holds in the fully-observed case with RIP constant $δ=0$. This benign nonconvexity, however, is unstable. It fails to extend to the partially-observed case with any arbitrarily small RIP constant $δ>0$, and to higher-rank ground truths $r^{\star}>1$, regardless of how much the search rank $r\ge r^{\star}$ is overparameterized. Together, these results undermine the standard stability-based explanation for the empirical success of nonconvex methods and suggest that fundamentally different tools are needed to analyze nonnegative low-rank recovery.
format Preprint
id arxiv_https___arxiv_org_abs_2505_03717
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Nonnegative Low-rank Matrix Recovery Can Have Spurious Local Minima
Zhang, Richard Y.
Optimization and Control
Machine Learning
Low-rank matrix recovery is well-known to exhibit benign nonconvexity under the restricted isometry property (RIP): every second-order critical point is globally optimal, so local methods provably recover the ground truth. Motivated by the strong empirical performance of projected gradient methods for nonnegative low-rank recovery problems, we investigate whether this benign geometry persists when the factor matrices are constrained to be elementwise nonnegative. In the simple setting of a rank-1 nonnegative ground truth, we confirm that benign nonconvexity holds in the fully-observed case with RIP constant $δ=0$. This benign nonconvexity, however, is unstable. It fails to extend to the partially-observed case with any arbitrarily small RIP constant $δ>0$, and to higher-rank ground truths $r^{\star}>1$, regardless of how much the search rank $r\ge r^{\star}$ is overparameterized. Together, these results undermine the standard stability-based explanation for the empirical success of nonconvex methods and suggest that fundamentally different tools are needed to analyze nonnegative low-rank recovery.
title Nonnegative Low-rank Matrix Recovery Can Have Spurious Local Minima
topic Optimization and Control
Machine Learning
url https://arxiv.org/abs/2505.03717