A Learned Proximal Alternating Minimization Algorithm and Its Induced Network for a Class of Two-Block Nonconvex and Nonsmooth Optimization

This work proposes a general learned proximal alternating minimization algorithm, LPAM, for solving learnable two-block nonsmooth and nonconvex optimization problems. We tackle the nonsmoothness by an appropriate smoothing technique with automatic diminishing smoothing effect. For smoothed nonconvex...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Journal of scientific computing Jg. 103; H. 2; S. 56
Hauptverfasser:	Chen, Yunmei, Liu, Lezhi, Zhang, Lei
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	New York Springer US 01.05.2025 Springer Nature B.V
Schlagworte:	Accumulation Algorithms Computational Mathematics and Numerical Analysis Computer vision Convergence Inverse problems Learning Machine learning Mathematical and Computational Engineering Mathematical and Computational Physics Mathematics Mathematics and Statistics Neural networks Optimization Optimization algorithms Smoothing Sparsity Theoretical Deep learning 68U10 65K05 MRI Image reconstruction Learned alternating minimization algorithm Nonconvex nonsmooth optimization 65K10 90C26
ISSN:	0885-7474, 1573-7691
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!