Learning nonlocal regularization operators

DOI10.3934/MCRF.2021003MaRDI QIDQ6333445zbMATH OpenFDO

Authors Gernot Holler, Karl Kunisch

Publication date 24 January 2020

Full work available at URL https://doi.org/10.3934/MCRF.2021003

Mathematics Subject Classification ID

Inverse problems for integral equations (45Q05) Existence theories for optimal control problems involving partial differential equations (49J20)

Abstract: A learning approach for determining which operator from a class of nonlocal operators is optimal for the regularization of an inverse problem is investigated. The considered class of nonlocal operators is motivated by the use of squared fractional order Sobolev seminorms as regularization operators. First fundamental results from the theory of regularization with local operators are extended to the nonlocal case. Then a framework based on a bilevel optimization strategy is developed which allows to choose nonlocal regularization operators from a given class which i) are optimal with respect to a suitable performance measure on a training set, and ii) enjoy particularly favorable properties. Results from numerical experiments are also provided.

This page was built for publication: Learning nonlocal regularization operators

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6333445)