Regularization Theory of the Analytic Deep Prior Approach

DOI10.1088/1361-6420/AC9011arXiv2205.06493MaRDI QIDQ6399062FDOQ6399062

Publication date: 13 May 2022

Abstract: The analytic deep prior (ADP) approach was recently introduced for the theoretical analysis of deep image prior (DIP) methods with special network architectures. In this paper, we prove that ADP is in fact equivalent to classical variational Ivanov methods for solving ill-posed inverse problems. Besides, we propose a new variant which incorporates the strategy of early stopping into the ADP model. For both variants, we show how classical regularization properties (existence, stability, convergence) can be obtained under common assumptions.

Mathematics Subject Classification ID

Linear operators and ill-posed problems, regularization (47A52)

This page was built for publication: Regularization Theory of the Analytic Deep Prior Approach

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6399062)