Local convergence of proximal splitting methods for rank constrained problems
(2018) 56th IEEE Annual Conference on Decision and Control, CDC 2017 2018-January. p.702-708- Abstract
We analyze the local convergence of proximal splitting algorithms to solve optimization problems that are convex besides a rank constraint. For this, we show conditions under which the proximal operator of a function involving the rank constraint is locally identical to the proximal operator of its convex envelope, hence implying local convergence. The conditions imply that the non-convex algorithms locally converge to a solution whenever a convex relaxation involving the convex envelope can be expected to solve the non-convex problem.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/4f4acfd8-f8d8-4647-bb6b-f8ac2d5311f6
- author
- Grussler, Christian LU and Giselsson, Pontus LU
- organization
- publishing date
- 2018-01-18
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- 2017 IEEE 56th Annual Conference on Decision and Control, CDC 2017
- volume
- 2018-January
- pages
- 7 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 56th IEEE Annual Conference on Decision and Control, CDC 2017
- conference location
- Melbourne, Australia
- conference dates
- 2017-12-12 - 2017-12-15
- external identifiers
-
- scopus:85046116353
- ISBN
- 9781509028733
- DOI
- 10.1109/CDC.2017.8263743
- language
- English
- LU publication?
- yes
- id
- 4f4acfd8-f8d8-4647-bb6b-f8ac2d5311f6
- date added to LUP
- 2018-05-15 13:37:46
- date last changed
- 2023-10-20 04:23:41
@inproceedings{4f4acfd8-f8d8-4647-bb6b-f8ac2d5311f6, abstract = {{<p>We analyze the local convergence of proximal splitting algorithms to solve optimization problems that are convex besides a rank constraint. For this, we show conditions under which the proximal operator of a function involving the rank constraint is locally identical to the proximal operator of its convex envelope, hence implying local convergence. The conditions imply that the non-convex algorithms locally converge to a solution whenever a convex relaxation involving the convex envelope can be expected to solve the non-convex problem.</p>}}, author = {{Grussler, Christian and Giselsson, Pontus}}, booktitle = {{2017 IEEE 56th Annual Conference on Decision and Control, CDC 2017}}, isbn = {{9781509028733}}, language = {{eng}}, month = {{01}}, pages = {{702--708}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, title = {{Local convergence of proximal splitting methods for rank constrained problems}}, url = {{http://dx.doi.org/10.1109/CDC.2017.8263743}}, doi = {{10.1109/CDC.2017.8263743}}, volume = {{2018-January}}, year = {{2018}}, }