Group Sparsity: A Unified Framework for Network Pruning and Neural Architecture Search
- We demonstrate how to exploit group sparsity in order to bridge the areas of network pruning and neural architecture search (NAS). This results in a new one-shot NAS optimizer that casts the problem as a single-level optimization problem and does not suffer any performance degradation from discretizating the architecture.
Document Type: | Conference Proceeding |
---|---|
Conference Type: | Konferenzartikel |
Zitierlink: | https://opus.hs-offenburg.de/5285 | Bibliografische Angaben |
Title (English): | Group Sparsity: A Unified Framework for Network Pruning and Neural Architecture Search |
Conference: | Workshop on Neural Architecture Search: IEEE/CVF Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 20-25 June 2021 |
Author: | Avraam Chatzimichailidis, Arber Zela, Shalini Shalini, Peter Labus, Janis KeuperStaff MemberORCiDGND, Frank Hutter, Yang Yang |
Year of Publication: | 2021 |
Contributing Corporation: | IEEE, Computer Vision Foundation |
Page Number: | 4 |
First Page: | 1 |
Last Page: | 4 |
Parent Title (English): | CVPR2021-NAS: Computer Society Conference on Computer Vision and Pattern Recognition : Workshop on Neural Architecture Search |
URL: | https://ml.informatik.uni-freiburg.de/wp-content/uploads/2022/03/Group_Sparsity.pdf |
Language: | English | Inhaltliche Informationen |
Institutes: | Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019) |
Forschung / IMLA - Institute for Machine Learning and Analytics | |
Institutes: | Bibliografie | Formale Angaben |
Open Access: | Open Access |
Licence (German): | Urheberrechtlich geschützt |