The effect of smooth parametrizations on nonconvex optimization landscapes
Mathematical Programming · 2025-01 · 209 (1-2) · 63-111
DOI: 10.1007/s10107-024-02058-3 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematical Programming, online erschienen am 04.03.2024. Verfasst von Eitan Levin und 2 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: EPFL Lausanne.
Abstract (Originalsprache)
We develop new tools to study landscapes in nonconvex optimization. Given one optimization problem, we pair it with another by smoothly parametrizing the domain. This is either for practical purposes (e.g., to use smooth optimization algorithms with good guarantees) or for theoretical purposes (e.g., to reveal that the landscape satisfies a strict saddle property). In both cases, the central question is: how do the landscapes of the two problems relate? More precisely: how do desirable points such as local minima and critical points in one problem relate to those in the other problem? A key finding in this paper is that these relations are often determined by the parametrization itself, and are almost entirely independent of the cost function. Accordingly, we introduce a general framework to study parametrizations by their effect on landscapes. The framework enables us to obtain new guarantees for an array of problems, some of which were previously treated on a case-by-case basis in the literature. Applications include: optimizing low-rank matrices and tensors through factorizations; solving semidefinite programs via the Burer–Monteiro approach; training neural networks by optimizing their weights and biases; and quotienting out symmetries.
Förderung
- EPFL Lausanne
Zitieren
APA
Levin, E., Kileel, J., & Boumal, N. (2025). The effect of smooth parametrizations on nonconvex optimization landscapes. Mathematical Programming, 209(1-2), 63-111. https://doi.org/10.1007/s10107-024-02058-3
Vancouver
Levin E, Kileel J, Boumal N. The effect of smooth parametrizations on nonconvex optimization landscapes. Mathematical Programming. 2025;209(1-2):63-111. doi:10.1007/s10107-024-02058-3
BibTeX
@article{Levin2025,
author = {Levin, Eitan and Kileel, Joe and Boumal, Nicolas},
title = {The effect of smooth parametrizations on nonconvex optimization landscapes},
journal = {Mathematical Programming},
year = {2025},
volume = {209},
number = {1-2},
pages = {63--111},
doi = {10.1007/s10107-024-02058-3}
}
EUVIMED