Paired Autoencoders for Likelihood-free Estimation in Inverse Problems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chung, Matthias, Hart, Emma, Chung, Julianne, Peters, Bas, Haber, Eldad
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912142214561792
author Chung, Matthias
Hart, Emma
Chung, Julianne
Peters, Bas
Haber, Eldad
author_facet Chung, Matthias
Hart, Emma
Chung, Julianne
Peters, Bas
Haber, Eldad
contents We consider the solution of nonlinear inverse problems where the forward problem is a discretization of a partial differential equation. Such problems are notoriously difficult to solve in practice and require minimizing a combination of a data-fit term and a regularization term. The main computational bottleneck of typical algorithms is the direct estimation of the data misfit. Therefore, likelihood-free approaches have become appealing alternatives. Nonetheless, difficulties in generalization and limitations in accuracy have hindered their broader utility and applicability. In this work, we use a paired autoencoder framework as a likelihood-free estimator for inverse problems. We show that the use of such an architecture allows us to construct a solution efficiently and to overcome some known open problems when using likelihood-free estimators. In particular, our framework can assess the quality of the solution and improve on it if needed. We demonstrate the viability of our approach using examples from full waveform inversion and inverse electromagnetic imaging.
format Preprint
id arxiv_https___arxiv_org_abs_2405_13220
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Paired Autoencoders for Likelihood-free Estimation in Inverse Problems
Chung, Matthias
Hart, Emma
Chung, Julianne
Peters, Bas
Haber, Eldad
Machine Learning
Artificial Intelligence
Numerical Analysis
We consider the solution of nonlinear inverse problems where the forward problem is a discretization of a partial differential equation. Such problems are notoriously difficult to solve in practice and require minimizing a combination of a data-fit term and a regularization term. The main computational bottleneck of typical algorithms is the direct estimation of the data misfit. Therefore, likelihood-free approaches have become appealing alternatives. Nonetheless, difficulties in generalization and limitations in accuracy have hindered their broader utility and applicability. In this work, we use a paired autoencoder framework as a likelihood-free estimator for inverse problems. We show that the use of such an architecture allows us to construct a solution efficiently and to overcome some known open problems when using likelihood-free estimators. In particular, our framework can assess the quality of the solution and improve on it if needed. We demonstrate the viability of our approach using examples from full waveform inversion and inverse electromagnetic imaging.
title Paired Autoencoders for Likelihood-free Estimation in Inverse Problems
topic Machine Learning
Artificial Intelligence
Numerical Analysis
url https://arxiv.org/abs/2405.13220