This work demonstrates how to use a piggyback-style algorithm to compute derivatives of loss functions that depend on solutions of convex-concave saddle-point problems. Two application scenarios are presented, where the piggyback primal-dual algorithm is used to learn an enhanced shearlet transform and an improved discretization of the second-order total generalized variation.

Full Paper

The PDF file did not load properly or your web browser does not support viewing PDF files. Download directly to your device: Download PDF document
Back to Top

Document information

Published on 26/05/23
Submitted on 26/05/23

Volume Adaptive Modelling, Optimisation and Learning Strategies for Image Analysis, 2023
Licence: CC BY-NC-SA license

Document Score


Views 0
Recommendations 0

Share this document

claim authorship

Are you one of the authors of this document?