University of Oulu

H. Y. Tan, S. Mukherjee, J. Tang, A. Hauptmann and C. -B. Schönlieb, "Robust Data-Driven Accelerated Mirror Descent," ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 2023, pp. 1-5, doi: 10.1109/ICASSP49357.2023.10096875

Robust data-driven accelerated mirror descent

Saved in:
Author: Tan, Hong Ye1; Mukherjee, Subhadip1,2; Tang, Junqi1;
Organizations: 1Damtp, University of Cambridge, Cambridge, U.K.
2Department of Computer Science, University of Bath, U.K.
3Research Unit of Mathematical Sciences, University of Oulu
4Department of Mathematics, University College London, London, U.K.
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 0.4 MB)
Persistent link:
Language: English
Published: Institute of Electrical and Electronics Engineers, 2023
Publish Date: 2023-07-10


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.

see all

Series: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing
ISSN: 1520-6149
ISSN-E: 2379-190X
ISSN-L: 1520-6149
ISBN: 978-1-7281-6327-7
ISBN Print: 978-1-7281-6328-4
Article number: 10096875
DOI: 10.1109/icassp49357.2023.10096875
Conference: IEEE International Conference on Acoustics, Speech and Signal Processing
Type of Publication: A4 Article in conference proceedings
Field of Science: 111 Mathematics
113 Computer and information sciences
Copyright information: © 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.