Inverse Problems with Learned Forward Operators

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Arridge, Simon, Hauptmann, Andreas, Korolev, Yury
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909138824462336
author Arridge, Simon
Hauptmann, Andreas
Korolev, Yury
author_facet Arridge, Simon
Hauptmann, Andreas
Korolev, Yury
contents Solving inverse problems requires the knowledge of the forward operator, but accurate models can be computationally expensive and hence cheaper variants that do not compromise the reconstruction quality are desired. This chapter reviews reconstruction methods in inverse problems with learned forward operators that follow two different paradigms. The first one is completely agnostic to the forward operator and learns its restriction to the subspace spanned by the training data. The framework of regularisation by projection is then used to find a reconstruction. The second one uses a simplified model of the physics of the measurement process and only relies on the training data to learn a model correction. We present the theory of these two approaches and compare them numerically. A common theme emerges: both methods require, or at least benefit from, training data not only for the forward operator, but also for its adjoint.
format Preprint
id arxiv_https___arxiv_org_abs_2311_12528
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Inverse Problems with Learned Forward Operators
Arridge, Simon
Hauptmann, Andreas
Korolev, Yury
Numerical Analysis
Machine Learning
65J22, 47A52, 35R30, 74J25
Solving inverse problems requires the knowledge of the forward operator, but accurate models can be computationally expensive and hence cheaper variants that do not compromise the reconstruction quality are desired. This chapter reviews reconstruction methods in inverse problems with learned forward operators that follow two different paradigms. The first one is completely agnostic to the forward operator and learns its restriction to the subspace spanned by the training data. The framework of regularisation by projection is then used to find a reconstruction. The second one uses a simplified model of the physics of the measurement process and only relies on the training data to learn a model correction. We present the theory of these two approaches and compare them numerically. A common theme emerges: both methods require, or at least benefit from, training data not only for the forward operator, but also for its adjoint.
title Inverse Problems with Learned Forward Operators
topic Numerical Analysis
Machine Learning
65J22, 47A52, 35R30, 74J25
url https://arxiv.org/abs/2311.12528