Metraipolis › archive › dc_d41e217c60dd
Low-rank matrix recovery landscapes beyond RIP with application to rank-one measurements — arXiv:2609.06146
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.06146
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T14:24:00.913Z
- SHA-256 of the archived text
629d1d47348721a6c17ff9926ed4899f1d06de4642048de3e8ac90a033afecd4- Stable URL of this page
https://metraipolis.com/documento/dc_d41e217c60dd
How to cite
Low-rank matrix recovery landscapes beyond RIP with application to rank-one measurements — arXiv:2609.06146 — arXiv (en), https://arxiv.org/abs/2609.06146 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d41e217c60dd (Metraipolis archive dc_d41e217c60dd, sha256 629d1d47348721a6c17ff9926ed4899f1d06de4642048de3e8ac90a033afecd4)
BibTeX
@misc{dcd41e217c60dd,
title = {Low-rank matrix recovery landscapes beyond RIP with application to rank-one measurements — arXiv:2609.06146},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.06146},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d41e217c60dd; sha256 629d1d47348721a6c17ff9926ed4899f1d06de4642048de3e8ac90a033afecd4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06146. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study the problem of low-rank matrix recovery from linear measurements via the global nonconvex landscape of a low-rank factored formulation of the matrix LASSO (nuclear-norm--regularized least-squares). If the landscape is benign, that is, has no bad local optima, then practical and scalable algorithms can compute good statistical estimates. Previous state-of-the-art landscape guarantees have typically assumed that the linear measurement operator has the restricted isometry property, that is, the operator is approximately an isometry over all low-rank matrices. This is an unrealistic assumption for many applications; in particular, when the individual measurement matrices are themselves low-rank, we typically have poor upper isometry constants. To overcome this, we establish new guarantees of a benign landscape under a weaker isometry condition: rather than requiring upper isometry over all low-rank matrices, we only require it over the linear low-rank tangent space to the low-rank ground truth matrix. To illustrate the utility of this result, we apply it to the problem of matrix recovery from random rank-one linear measurements; via high-probability concentration bounds on the random measurement operator, we prove a novel landscape guarantee with statistically near-optimal sample complexity and recovery error. Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-09-09 in math.OC). Categorie arXiv: Optimization and Control (math.OC) ; Information Theory (cs.IT); Statistics Theory (math.ST). Pagina del lavoro: https://arxiv.org/abs/2609.06146 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T14:09:21.656Z dalla pagina https://arxiv.org/catchup/math.OC/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).