Robust Data-Driven Accelerated Mirror Descent
From MaRDI portal
Publication:6414724
DOI10.1109/ICASSP49357.2023.10096875arXiv2210.12238MaRDI QIDQ6414724FDOQ6414724
Authors: Subhadip Mukherjee, J. Tang, Andreas Hauptmann, Carola-Bibiane Schönlieb 
Publication date: 21 October 2022
Abstract: Learning-to-optimize is an emerging framework that leverages training data to speed up the solution of certain optimization problems. One such approach is based on the classical mirror descent algorithm, where the mirror map is modelled using input-convex neural networks. In this work, we extend this functional parameterization approach by introducing momentum into the iterations, based on the classical accelerated mirror descent. Our approach combines short-time accelerated convergence with stable long-time behavior. We empirically demonstrate additional robustness with respect to multiple parameters on denoising and deconvolution experiments.
This page was built for publication: Robust Data-Driven Accelerated Mirror Descent
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6414724)
