Generalized Qualification and Qualification Levels for Spectral Regularization Methods
Terry Herdman, Ruben D. Spies, Karina G. Temperini

TL;DR
This paper extends the concept of qualification for spectral regularization methods in inverse problems, introducing weak, strong, and optimal levels, and analyzing their implications for convergence and source sets.
Contribution
It introduces a generalized qualification framework with three levels, broadening the understanding of convergence orders for spectral regularization methods.
Findings
Weak qualification extends previous definitions.
Methods with infinite classical qualification can have generalized qualification.
Conditions for each qualification level are characterized.
Abstract
The concept of qualification for spectral regularization methods for inverse ill-posed problems is strongly associated to the optimal order of convergence of the regularization error. In this article, the definition of qualification is extended and three different levels are introduced: weak, strong and optimal. It is shown that the weak qualification extends the definition introduced by Mathe and Pereverzev in 2003, mainly in the sense that the functions associated to orders of convergence and source sets need not be the same. It is shown that certain methods possessing infinite classical qualification, e.g. truncated singular value decomposition (TSVD), Landweber's method and Showalter's method, also have generalized qualification leading to an optimal order of convergence of the regularization error. Sufficient conditions for a SRM to have weak qualification are provided and…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
