Hybrid Least Squares for Learning Functions from Highly Noisy Data
SIAM Journal on Mathematics of Data Science · 31.12.2026 · 8 (4) · 1370-1392
DOI: 10.1137/25m1775968 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Mathematics of Data Science, online erschienen am 13.11.2026. Verfasst von Ben Adcock und 3 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Gefördert von: AMS-Simons, Air Force Office of Scientific Research, Natural Sciences and Engineering Research Council of Canada.
Abstract (Originalsprache)
Motivated by the need for efficient estimation of conditional expectations, we consider a least-squares function approximation problem with heavily polluted data. Existing methods that are effective in the small-noise regime are suboptimal when large noise is present. To address this issue, we propose a hybrid approach that combines Christoffel sampling with optimal experimental design. We show that the proposed algorithm enjoys appropriate optimality properties for both sample point generation and noise mollification, leading to improved computational efficiency and sample complexity compared to existing methods. We also extend the algorithm to convexity-constrained settings with similar theoretical guarantees. When the target function is defined as the expectation of a random field, we further extend our approach to leverage adaptive random subspaces and establish results on the approximation capacity of the adaptive procedure. Our theoretical findings are supported by numerical studies on both synthetic data and a more challenging stochastic simulation problem in computational finance.
Förderung
- AMS-Simons
- Air Force Office of Scientific Research
- Natural Sciences and Engineering Research Council of Canada
- National Science Foundation
- University of Kentucky
Zitieren
APA
Adcock, B., Hientzsch, B., Narayan, A., & Xu, Y. (2026). Hybrid Least Squares for Learning Functions from Highly Noisy Data. SIAM Journal on Mathematics of Data Science, 8(4), 1370-1392. https://doi.org/10.1137/25m1775968
Vancouver
Adcock B, Hientzsch B, Narayan A, Xu Y. Hybrid Least Squares for Learning Functions from Highly Noisy Data. SIAM Journal on Mathematics of Data Science. 2026;8(4):1370-1392. doi:10.1137/25m1775968
BibTeX
@article{Adcock2026,
author = {Adcock, Ben and Hientzsch, Bernhard and Narayan, Akil and Xu, Yiming},
title = {Hybrid Least Squares for Learning Functions from Highly Noisy Data},
journal = {SIAM Journal on Mathematics of Data Science},
year = {2026},
volume = {8},
number = {4},
pages = {1370--1392},
doi = {10.1137/25m1775968}
}
EUVIMED