EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Nonconvex matrix factorization is geodesically convex: global landscape analysis for fixed-rank matrix optimization from a Riemannian perspective

Yuetian Luo, Nicolás García Trillos

Mathematical Programming · 22.07.2026

DOI: 10.1007/s10107-026-02400-x ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematical Programming, online erschienen am 22.07.2026. Verfasst von Yuetian Luo und 1 weiteren Autor:innen. Die Arbeit nennt 89 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Directorate for Mathematical and Physical Sciences.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this paper we study the landscape of a general matrix optimization problem with a fixed-rank positive semidefinite (PSD) constraint. We perform the Burer-Monteiro factorization, i.e., factorize a PSD matrix $${\textbf{X}}$$ X as $${\textbf{Y}}{\textbf{Y}}^\top $$ Y Y ⊤ , and consider a particular Riemannian quotient geometry in a search space that has a total space equipped with the Euclidean metric. When the original objective f satisfies standard restricted strong convexity and smoothness properties, we characterize the global landscape of the factorized objective under the Riemannian quotient geometry. In particular, we show that the entire search space can be divided into three regions: ( $$\mathcal{R}_1$$ R 1 ) the region near the target parameter of interest, where the factorized objective is geodesically strongly convex and smooth; ( $$\mathcal{R}_2$$ R 2 ) the region containing neighborhoods of all strict saddle points; ( $$\mathcal{R}_3$$ R 3 ) the remaining regions, where the factorized objective has a large gradient. Our results cover both noisy and noiseless settings in applications of interest. To the best of our knowledge, this is the first global landscape analysis of the Burer-Monteiro factorized objective under the Riemannian quotient geometry. Our results provide a fully geometric explanation for the superior performance of vanilla gradient descent under the Burer-Monteiro factorization. When f satisfies a weaker restricted strict convexity property, we show there exists a neighborhood near local minimizers such that the factorized objective is geodesically convex. To prove our main results we provide a comprehensive landscape analysis of a matrix factorization problem with a least squares objective, which serves as a critical bridge in establishing the results in the general setting. Our conclusions are also based on a result of independent interest stating that the geodesic ball centered at $${\textbf{Y}}$$ Y with a radius one-third of the least singular value of $${\textbf{Y}}$$ Y is a geodesically convex set under the Riemannian quotient geometry, a result that, as a corollary, also implies a quantitative bound of the convexity radius in the Bures-Wasserstein space. The convexity radius obtained in this paper is sharp up to constants.

Förderung

  • Directorate for Mathematical and Physical Sciences

Zitieren

APA

Luo, Y., & Trillos, N. G. (2026). Nonconvex matrix factorization is geodesically convex: global landscape analysis for fixed-rank matrix optimization from a Riemannian perspective. Mathematical Programming. https://doi.org/10.1007/s10107-026-02400-x

Vancouver

Luo Y, Trillos NG. Nonconvex matrix factorization is geodesically convex: global landscape analysis for fixed-rank matrix optimization from a Riemannian perspective. Mathematical Programming. 2026. doi:10.1007/s10107-026-02400-x

BibTeX
@article{Luo2026,
  author = {Luo, Yuetian and Trillos, Nicolás García},
  title = {Nonconvex matrix factorization is geodesically convex: global landscape analysis for fixed-rank matrix optimization from a Riemannian perspective},
  journal = {Mathematical Programming},
  year = {2026},
  doi = {10.1007/s10107-026-02400-x}
}
Kostenlos starten →