Universal Architectures for the Learning of Polyhedral Norms and Convex Regularizers
SIAM Journal on Imaging Sciences · 30.06.2026 · 19 (2) · 1272-1299
DOI: 10.1137/25m176297x ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Imaging Sciences, online erschienen am 04.06.2026. Verfasst von Michael Unser und 1 weiteren Autor:innen. Die Arbeit nennt 80 Literaturangaben. Gefördert von: H2020 European Research Council.
Abstract (Originalsprache)
This paper addresses the task of learning convex regularizers to guide the reconstruction of images from limited data. By imposing that the reconstruction be amplitude-equivariant, we narrow down the class of admissible functionals to those that can be expressed as a power of a seminorm. We then show that such functionals can be approximated to arbitrary precision with the help of polyhedral norms. In particular, we identify two dual parameterizations of such systems: (i) a synthesis (or atomic) form with an [Formula: see text]-penalty that involves some learnable dictionary; and (ii) an analysis form with an [Formula: see text]-penalty that involves a trainable regularization operator. After having provided geometric insights and proved that the two forms are universal, we propose an implementation that relies on a specific architecture (tight frame with a weighted [Formula: see text] penalty) that is easy to train. We illustrate its use for denoising and the reconstruction of biomedical images. We find that the proposed framework outperforms the sparsity-based methods of compressed sensing, while it offers essentially the same convergence and robustness guarantees.
Förderung
- H2020 European Research Council
Zitieren
APA
Unser, M., & Ducotterd, S. (2026). Universal Architectures for the Learning of Polyhedral Norms and Convex Regularizers. SIAM Journal on Imaging Sciences, 19(2), 1272-1299. https://doi.org/10.1137/25m176297x
Vancouver
Unser M, Ducotterd S. Universal Architectures for the Learning of Polyhedral Norms and Convex Regularizers. SIAM Journal on Imaging Sciences. 2026;19(2):1272-1299. doi:10.1137/25m176297x
BibTeX
@article{Unser2026,
author = {Unser, Michael and Ducotterd, Stanislas},
title = {Universal Architectures for the Learning of Polyhedral Norms and Convex Regularizers},
journal = {SIAM Journal on Imaging Sciences},
year = {2026},
volume = {19},
number = {2},
pages = {1272--1299},
doi = {10.1137/25m176297x}
}
EUVIMED