On Optimal Regularization Parameters via Bilevel Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ehrhardt, Matthias J., Gazzola, Silvia, Scott, Sebastian J.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914646467805184
author Ehrhardt, Matthias J.
Gazzola, Silvia
Scott, Sebastian J.
author_facet Ehrhardt, Matthias J.
Gazzola, Silvia
Scott, Sebastian J.
contents Variational regularization is commonly used to solve linear inverse problems, and involves augmenting a data fidelity by a regularizer. The regularizer is used to promote a priori information and is weighted by a regularization parameter. Selection of an appropriate regularization parameter is critical, with various choices leading to very different reconstructions. Classical strategies used to determine a suitable parameter value include the discrepancy principle and the L-curve criterion, and in recent years a supervised machine learning approach called bilevel learning has been employed. Bilevel learning is a powerful framework to determine optimal parameters and involves solving a nested optimization problem. While previous strategies enjoy various theoretical results, the well-posedness of bilevel learning in this setting is still an open question. In particular, a necessary property is positivity of the determined regularization parameter. In this work, we provide a new condition that better characterizes positivity of optimal regularization parameters than the existing theory. Numerical results verify and explore this new condition for both small and high-dimensional problems.
format Preprint
id arxiv_https___arxiv_org_abs_2305_18394
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle On Optimal Regularization Parameters via Bilevel Learning
Ehrhardt, Matthias J.
Gazzola, Silvia
Scott, Sebastian J.
Optimization and Control
Machine Learning
65K10 (Primary) 65F22 (Secondary)
Variational regularization is commonly used to solve linear inverse problems, and involves augmenting a data fidelity by a regularizer. The regularizer is used to promote a priori information and is weighted by a regularization parameter. Selection of an appropriate regularization parameter is critical, with various choices leading to very different reconstructions. Classical strategies used to determine a suitable parameter value include the discrepancy principle and the L-curve criterion, and in recent years a supervised machine learning approach called bilevel learning has been employed. Bilevel learning is a powerful framework to determine optimal parameters and involves solving a nested optimization problem. While previous strategies enjoy various theoretical results, the well-posedness of bilevel learning in this setting is still an open question. In particular, a necessary property is positivity of the determined regularization parameter. In this work, we provide a new condition that better characterizes positivity of optimal regularization parameters than the existing theory. Numerical results verify and explore this new condition for both small and high-dimensional problems.
title On Optimal Regularization Parameters via Bilevel Learning
topic Optimization and Control
Machine Learning
65K10 (Primary) 65F22 (Secondary)
url https://arxiv.org/abs/2305.18394