Provably Convergent Data-Driven Convex-Nonconvex Regularization

An emerging new paradigm for solving inverse problems is via the use of deep learning to learn a regularizer from data. This leads to high-quality results, but often at the cost of provable guarantees. In this work, we show how well-posedness and convergent regularization arises within the convex-no...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-11
Hauptverfasser:	Shumaylov, Zakhar, Budd, Jeremy, Mukherjee, Subhadip, Schönlieb, Carola-Bibiane
Format:	Artikel
Sprache:	eng
Schlagworte:	Convergence Inverse problems Neural networks Regularization
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!