EUVIMEDEUVIMED entdecken
Open Access

GNMR: A Provable One-Line Algorithm for Low Rank Matrix Recovery

Pini Zilber, Boaz Nadler

SIAM Journal on Mathematics of Data Science · 2022-06 · 4 (2) · 909-934

DOI: 10.1137/21m1433812 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SIAM Journal on Mathematics of Data Science, online erschienen am 28.06.2022. Verfasst von Pini Zilber und 1 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Mathematics and Computer Science, Weizmann Institute of Science, Rehovot 7610001 Israel. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 83 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIGMS NIH HHS, National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Low rank matrix recovery problems appear in a broad range of applications. In this work we present GNMR---an extremely simple iterative algorithm for low rank matrix recovery, based on a Gauss--Newton linearization. On the theoretical front, we derive recovery guarantees for GNMR in both matrix sensing and matrix completion settings. Some of these results improve upon the best currently known for other methods. A key property of GNMR is that it implicitly keeps the factor matrices approximately balanced throughout its iterations. On the empirical front, we show that for matrix completion with uniform sampling, GNMR performs better than several popular methods, especially when given very few observations close to the information limit.

Schlagwörter

Stichwörter der Autor:innen

15A8349M1565F55Gauss–Newtonlow rank matricesmatrix completionmatrix recoverymatrix sensing

Autor:innen und Institutionen

  • Faculty of Mathematics and Computer Science, Weizmann Institute of Science, Rehovot 7610001 Israel.

Förderung

  • NIGMS NIH HHS
  • National Institutes of Health

Zitieren

APA

Zilber, P., & Nadler, B. (2022). GNMR: A Provable One-Line Algorithm for Low Rank Matrix Recovery. SIAM Journal on Mathematics of Data Science, 4(2), 909-934. https://doi.org/10.1137/21m1433812

Vancouver

Zilber P, Nadler B. GNMR: A Provable One-Line Algorithm for Low Rank Matrix Recovery. SIAM Journal on Mathematics of Data Science. 2022;4(2):909-934. doi:10.1137/21m1433812

BibTeX
@article{Zilber2022,
  author = {Zilber, Pini and Nadler, Boaz},
  title = {GNMR: A Provable One-Line Algorithm for Low Rank Matrix Recovery},
  journal = {SIAM Journal on Mathematics of Data Science},
  year = {2022},
  volume = {4},
  number = {2},
  pages = {909--934},
  doi = {10.1137/21m1433812}
}
Kostenlos starten →