EUVIMEDEUVIMED entdecken
Crossref

Method of Moments for Estimation of Noisy Curves

Phillip Lo, Yuehaw Khoo

SIAM Journal on Mathematics of Data Science · 31.03.2026 · 8 (1) · 200-223

DOI: 10.1137/24m1711248 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SIAM Journal on Mathematics of Data Science, online erschienen am 04.03.2026. Verfasst von Phillip Lo und 1 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben. Gefördert von: National Science Foundation, U.S. Department of Energy, Sloan Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this paper, we study the problem of recovering a ground truth high dimensional piecewise linear curve [Formula: see text] from a high noise Gaussian point cloud with covariance [Formula: see text] centered around the curve. We establish that the sample complexity of recovering [Formula: see text] from data scales with order at least [Formula: see text]. We then show that recovery of a piecewise linear curve from the third moment is locally well-posed and, hence, [Formula: see text] samples are also sufficient for recovery. We propose methods to recover a curve from data based on a fitting to the third moment tensor with a careful initialization strategy and conduct some numerical experiments verifying the ability of our methods to recover curves. All code for our numerical experiments is publicly available on GitHub.

Förderung

  • National Science Foundation
  • U.S. Department of Energy
  • Sloan Foundation

Zitieren

APA

Lo, P., & Khoo, Y. (2026). Method of Moments for Estimation of Noisy Curves. SIAM Journal on Mathematics of Data Science, 8(1), 200-223. https://doi.org/10.1137/24m1711248

Vancouver

Lo P, Khoo Y. Method of Moments for Estimation of Noisy Curves. SIAM Journal on Mathematics of Data Science. 2026;8(1):200-223. doi:10.1137/24m1711248

BibTeX
@article{Lo2026,
  author = {Lo, Phillip and Khoo, Yuehaw},
  title = {Method of Moments for Estimation of Noisy Curves},
  journal = {SIAM Journal on Mathematics of Data Science},
  year = {2026},
  volume = {8},
  number = {1},
  pages = {200--223},
  doi = {10.1137/24m1711248}
}
Kostenlos starten →