Learning Sparsity-Promoting Regularizers for Linear Inverse Problems
SIAM Journal on Mathematics of Data Science · 31.03.2026 · 8 (1) · 167-199
DOI: 10.1137/24m1719785 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Mathematics of Data Science, online erschienen am 02.03.2026. Verfasst von Giovanni S. Alberti und 5 weiteren Autor:innen. Die Arbeit nennt 50 Literaturangaben. Gefördert von: Air Force Office of Scientific Research, European Union, Research Council of Finland.
Abstract (Originalsprache)
This paper introduces a novel approach to learning sparsity-promoting regularizers for solving linear inverse problems. We develop a bilevel optimization framework to select an optimal synthesis operator, denoted as [Formula: see text], which regularizes the inverse problem while promoting sparsity in the solution. The method leverages statistical properties of the underlying data and incorporates prior knowledge through the choice of [Formula: see text]. We establish the well-posedness of the optimization problem, provide theoretical guarantees for the learning process, and present sample complexity bounds. The approach is demonstrated through theoretical infinite-dimensional examples, including compact perturbations of a known operator and the problem of learning the mother wavelet, and through extensive numerical simulations. This work extends previous efforts in Tikhonov regularization by addressing nondifferentiable norms and proposing a data-driven approach to sparse regularization in infinite dimensions.
Förderung
- Air Force Office of Scientific Research
- European Union
- Research Council of Finland
Zitieren
APA
Alberti, G. S., Vito, E. D., Helin, T., Lassas, M., Ratti, L., & Santacesaria, M. (2026). Learning Sparsity-Promoting Regularizers for Linear Inverse Problems. SIAM Journal on Mathematics of Data Science, 8(1), 167-199. https://doi.org/10.1137/24m1719785
Vancouver
Alberti GS, Vito ED, Helin T, Lassas M, Ratti L, Santacesaria M. Learning Sparsity-Promoting Regularizers for Linear Inverse Problems. SIAM Journal on Mathematics of Data Science. 2026;8(1):167-199. doi:10.1137/24m1719785
BibTeX
@article{Alberti2026,
author = {Alberti, Giovanni S. and Vito, Ernesto De and Helin, Tapio and Lassas, Matti and Ratti, Luca and Santacesaria, Matteo},
title = {Learning Sparsity-Promoting Regularizers for Linear Inverse Problems},
journal = {SIAM Journal on Mathematics of Data Science},
year = {2026},
volume = {8},
number = {1},
pages = {167--199},
doi = {10.1137/24m1719785}
}
EUVIMED