Convergence Rates for Tikhonov Regularization on Compact Sets: Application to Neural Networks

Abstract. In this work, we consider ill-posed inverse problems in which the forward operator is continuous and weakly closed, and the sought solution belongs to a weakly closed constraint set. We propose a regularization method based on minimizing the Tikhonov functional on a sequence of compact sets which is dense in the intersection between the domain of the forward operator and the constraint set. The index of the compact sets can be interpreted as an additional regularization parameter. We prove that the proposed method is a regularization, achieving the same convergence rates as classical Tikhonov regularization and attaining the optimal convergence rate when the forward operator is linear. Moreover, we show that our methodology applies to the case where the constrained solution space is parametrized by means of neural networks (NNs), and the constraint is obtained by composing the last layer of the NN with a suitable activation function. In this case, the dense compact sets are defined by taking a family of bounded weight NNs with increasing weight bound. Finally, we present numerical experiments for both the standard and the attenuated Radon transforms. First, we compare the theoretical behavior of the reconstruction error with that obtained in a finite-dimensional and nonasymptotic setting. We then assess the performance of the method with respect to the classical nonnegative Tikhonov method and a recent Plug-and-Play reconstruction approach.

Authors

Institutions

Publication Details

Journal
SIAM Journal on Numerical Analysis
Published
2026-11-16
DOI
https://doi.org/10.1137/25m1762774
Primary Topic
Numerical methods in inverse problems
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Convergence Rates for Tikhonov Regularization on Compact Sets: Application to Neural Networks

Federico Benvenuto
SIAM Journal on Numerical Analysis
Numerical methods in inverse problems
article

Convergence Rates for Tikhonov Regularization on Compact Sets: Application to Neural Networks

Federico Benvenuto
article en

Abstract

Abstract. In this work, we consider ill-posed inverse problems in which the forward operator is continuous and weakly closed, and the sought solution belongs to a weakly closed constraint set. We propose a regularization method based on minimizing the Tikhonov functional on a sequence of compact sets which is dense in the intersection between the domain of the forward operator and the constraint set. The index of the compact sets can be interpreted as an additional regularization parameter. We prove that the proposed method is a regularization, achieving the same convergence rates as classical Tikhonov regularization and attaining the optimal convergence rate when the forward operator is linear. Moreover, we show that our methodology applies to the case where the constrained solution space is parametrized by means of neural networks (NNs), and the constraint is obtained by composing the last layer of the NN with a suitable activation function. In this case, the dense compact sets are defined by taking a family of bounded weight NNs with increasing weight bound. Finally, we present numerical experiments for both the standard and the attenuated Radon transforms. First, we compare the theoretical behavior of the reconstruction error with that obtained in a finite-dimensional and nonasymptotic setting. We then assess the performance of the method with respect to the classical nonnegative Tikhonov method and a recent Plug-and-Play reconstruction approach.

SIAM Journal on Numerical AnalysisVol. 64(6)
FHNW University of Applied Sciences and Arts Northwestern Switzerland (CH), University of Genoa (IT)
National Science Foundation, Istituto Nazionale di Alta Matematica "Francesco Severi", Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung, Gruppo Nazionale per il Calcolo Scientifico, High Energy Physics
Numerical methods in inverse problems
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon