Metraipolis › archive › dc_ff7449e338c7
Unique sparse decomposition of low rank matrices — arXiv:2106.07736
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2106.07736
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T08:27:56.717Z
- SHA-256 of the archived text
37d3b6982a140e8e62b2c92727ddcfab9e82b847386c5db373375829734b1c25- Stable URL of this page
https://metraipolis.com/documento/dc_ff7449e338c7
How to cite
Unique sparse decomposition of low rank matrices — arXiv:2106.07736 — arXiv (en), https://arxiv.org/abs/2106.07736 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff7449e338c7 (Metraipolis archive dc_ff7449e338c7, sha256 37d3b6982a140e8e62b2c92727ddcfab9e82b847386c5db373375829734b1c25)
BibTeX
@misc{dcff7449e338c7,
title = {Unique sparse decomposition of low rank matrices — arXiv:2106.07736},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2106.07736},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff7449e338c7; sha256 37d3b6982a140e8e62b2c92727ddcfab9e82b847386c5db373375829734b1c25},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2106.07736. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The problem of finding the unique low dimensional decomposition of a given matrix has been a fundamental and recurrent problem in many areas. In this paper, we study the problem of seeking a unique decomposition of a low rank matrix $Y\in \mathbb{R}^{p\times n}$ that admits a sparse representation. Specifically, we consider $Y = A X\in \mathbb{R}^{p\times n}$ where the matrix $A\in \mathbb{R}^{p\times r}$ has full column rank, with $r < \min\{n,p\}$, and the matrix $X\in \mathbb{R}^{r\times n}$ is element-wise sparse. We prove that this sparse decomposition of $Y$ can be uniquely identified, up to some intrinsic signed permutation. Our approach relies on solving a nonconvex optimization problem constrained over the unit sphere. Our geometric analysis for the nonconvex optimization landscape shows that any {\em strict} local solution is close to the ground truth solution, and can be recovered by a simple data-driven initialization followed with any second order descent algorithm. At last, we corroborate these theoretical results with numerical experiments.
Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-08-25 in math.NA).
Categorie arXiv: Optimization and Control (math.OC) ; Machine Learning (cs.LG); Signal Processing (eess.SP); Numerical Analysis (math.NA); Statistics Theory (math.ST).
Pagina del lavoro: https://arxiv.org/abs/2106.07736 — 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 2026-10-18T08:27:23.858Z dalla pagina https://arxiv.org/catchup/math.NA/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).