Year: 2022
Type: article
Abstract: In this work, we investigate various approaches that use learning from training data to solve inverse problems, following a bi-level learning approach. We consider a general framework for optimal inversion design, where training data can be used to learn optimal regularization parameters, data fidelity terms, and regularizers, thereby resulting in superior variational regularization methods. In particular, we describe methods to learn optimal $ p $ and $ q $ norms for $ {\rm L}^p-{\rm L}^q $ regularization and methods to learn optimal parameters for regularization matrices defined by covariance kernels. We exploit efficient algorithms based on Krylov projection methods for solving the regularized problems, both at training and validation stages, making these methods well-suited for large-scale problems. Our experiments show that the learned regularization methods perform well even when there is some inexactness in the forward operator, resulting in a mixture of model and measurement error.
DOI: 10.3934/naco.2022036
Institutions: Emory University, University of Bath, Tufts University
Language: English
Subfield: Mathematical Physics
Field: Mathematics
Domain: Physical Sciences
Open Access status: diamond
Awards: G10459543, G1086364909, G1430382554, Fast and Flexible Solvers for Inverse Problems, G2468938559, CAREER: Integrated Approaches for Fast and Accurate Large-Scale Inversion, G5222372538, RTG: Data-Oriented Mathematical and Statistical Sciences, G5754248372, Collaborative Research: Stochastic Approximations for the Solution and Uncertainty Analysis of Data-Intensive Inverse Problems
OpenAlex ID: W3202354099
