Denoising Guarantees for Optimized Sampling Schemes in Compressed Sensing
SIAM Journal on Mathematics of Data Science · 30.06.2026 · 8 (2) · 471-494
DOI: 10.1137/25m1746707 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Mathematics of Data Science, online erschienen am 15.06.2026. Verfasst von Yaniv Plan und 3 weiteren Autor:innen. Die Arbeit nennt 29 Literaturangaben. Gefördert von: Natural Sciences and Engineering Research Council of Canada, Pacific Institute for the Mathematical Sciences, CNRS - PIMS International Research Laboratory.
Abstract (Originalsprache)
Compressed sensing with subsampled unitary matrices benefits from optimized sampling schemes, which feature improved theoretical guarantees and empirical performance relative to uniform subsampling. We provide first-of-their-kind theoretical guarantees for compressed sensing, showing that the error caused by the measurement noise vanishes with an increasing number of measurements for optimized sampling schemes, assuming that the noise is Gaussian. We moreover provide similar guarantees for measurements sampled with replacement with arbitrary probability weights. All our results hold on prior sets contained in a union of low-dimensional subspaces. Finally, we demonstrate that this denoising behavior appears in empirical experiments with a rate that closely matches our theoretical guarantees when the prior set is the range of a generative ReLU neural network and when it is the set of sparse vectors.
Förderung
- Natural Sciences and Engineering Research Council of Canada
- Pacific Institute for the Mathematical Sciences
- CNRS - PIMS International Research Laboratory
Zitieren
APA
Plan, Y., Scott, M. S., Sheng, X., & Yilmaz, O. (2026). Denoising Guarantees for Optimized Sampling Schemes in Compressed Sensing. SIAM Journal on Mathematics of Data Science, 8(2), 471-494. https://doi.org/10.1137/25m1746707
Vancouver
Plan Y, Scott MS, Sheng X, Yilmaz O. Denoising Guarantees for Optimized Sampling Schemes in Compressed Sensing. SIAM Journal on Mathematics of Data Science. 2026;8(2):471-494. doi:10.1137/25m1746707
BibTeX
@article{Plan2026,
author = {Plan, Yaniv and Scott, Matthew S. and Sheng, Xia and Yilmaz, Ozgur},
title = {Denoising Guarantees for Optimized Sampling Schemes in Compressed Sensing},
journal = {SIAM Journal on Mathematics of Data Science},
year = {2026},
volume = {8},
number = {2},
pages = {471--494},
doi = {10.1137/25m1746707}
}
EUVIMED