Convergence analysis of equilibrium methods for inverse problems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Obmann, Daniel, Hwang, Gyeongha, Haltmeier, Markus
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909798759399424
author Obmann, Daniel
Hwang, Gyeongha
Haltmeier, Markus
author_facet Obmann, Daniel
Hwang, Gyeongha
Haltmeier, Markus
contents Solving inverse problems \(Ax = y\) is central to a variety of practically important fields such as medical imaging, remote sensing, and non-destructive testing. The most successful and theoretically best-understood method is convex variational regularization, where approximate but stable solutions are defined as minimizers of \( \|A(\cdot) - y^δ\|^2 / 2 + α\mathcal{R}(\cdot)\), with \(\mathcal{R}\) a regularization functional. Recent methods such as deep equilibrium models and plug-and-play approaches, however, go beyond variational regularization. Motivated by these innovations, we introduce implicit non-variational (INV) regularization, where approximate solutions are defined as solutions of \(A^*(A x - y^δ) + αR(x) = 0\) for some regularization operator \(R\). When the regularization operator is the gradient of a functional, INV reduces to classical variational regularization. However, in methods like DEQ and PnP, \(R\) is not a gradient field, and the existing theoretical foundation remains incomplete. To address this, we establish stability and convergence results in this broader setting, including convergence rates and stability estimates measured via a absolute Bregman distance.
format Preprint
id arxiv_https___arxiv_org_abs_2306_01421
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Convergence analysis of equilibrium methods for inverse problems
Obmann, Daniel
Hwang, Gyeongha
Haltmeier, Markus
Numerical Analysis
Computer Vision and Pattern Recognition
Solving inverse problems \(Ax = y\) is central to a variety of practically important fields such as medical imaging, remote sensing, and non-destructive testing. The most successful and theoretically best-understood method is convex variational regularization, where approximate but stable solutions are defined as minimizers of \( \|A(\cdot) - y^δ\|^2 / 2 + α\mathcal{R}(\cdot)\), with \(\mathcal{R}\) a regularization functional. Recent methods such as deep equilibrium models and plug-and-play approaches, however, go beyond variational regularization. Motivated by these innovations, we introduce implicit non-variational (INV) regularization, where approximate solutions are defined as solutions of \(A^*(A x - y^δ) + αR(x) = 0\) for some regularization operator \(R\). When the regularization operator is the gradient of a functional, INV reduces to classical variational regularization. However, in methods like DEQ and PnP, \(R\) is not a gradient field, and the existing theoretical foundation remains incomplete. To address this, we establish stability and convergence results in this broader setting, including convergence rates and stability estimates measured via a absolute Bregman distance.
title Convergence analysis of equilibrium methods for inverse problems
topic Numerical Analysis
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2306.01421