Saved in:
Bibliographic Details
Main Authors: Alberti, Giovanni S., De Vito, Ernesto, Helin, Tapio, Lassas, Matti, Ratti, Luca, Santacesaria, Matteo
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.16031
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910037181464576
author Alberti, Giovanni S.
De Vito, Ernesto
Helin, Tapio
Lassas, Matti
Ratti, Luca
Santacesaria, Matteo
author_facet Alberti, Giovanni S.
De Vito, Ernesto
Helin, Tapio
Lassas, Matti
Ratti, Luca
Santacesaria, Matteo
contents 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 $B$, 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 $B$. 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 non-differentiable norms and proposing a data-driven approach for sparse regularization in infinite dimensions.
format Preprint
id arxiv_https___arxiv_org_abs_2412_16031
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Learning sparsity-promoting regularizers for linear inverse problems
Alberti, Giovanni S.
De Vito, Ernesto
Helin, Tapio
Lassas, Matti
Ratti, Luca
Santacesaria, Matteo
Machine Learning
Statistics Theory
65J22, 68T05
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 $B$, 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 $B$. 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 non-differentiable norms and proposing a data-driven approach for sparse regularization in infinite dimensions.
title Learning sparsity-promoting regularizers for linear inverse problems
topic Machine Learning
Statistics Theory
65J22, 68T05
url https://arxiv.org/abs/2412.16031