Quadratic error bound of the smoothed gap and the restarted averaged primal-dual hybrid gradient
We study the linear convergence of the primal-dual hybrid gradient method. After a review of current analyses, we show that they do not explain properly the behavior of the algorithm, even on the most simple problems. We thus introduce the quadratic error bound of the smoothed gap, a new regularity...
Saved in:
| Main Author: | Fercoq, Olivier |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Université de Montpellier
2023-08-01
|
| Series: | Open Journal of Mathematical Optimization |
| Subjects: | |
| Online Access: | https://ojmo.centre-mersenne.org/articles/10.5802/ojmo.26/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Backtracking Restarts for Deep Reinforcement Learning
by: Zaid Khalil Marji, et al.
Published: (2021-04-01) -
Business Restart in Visegrad Countries
by: Marian Holienka, et al.
Published: (2014-03-01) -
Do not Let Your Primal World Beliefs Burn You Out: An Initial Unravelling of the Role of Primal World Beliefs in Core Burnout Symptoms Experience
by: Pavol Kačmár, et al.
Published: (2025-06-01) -
Continuous functions on primal topological spaces induced by group actions
by: Luis Fernando Mejías, et al.
Published: (2025-01-01) -
Distributed quantile regression over sensor networks via the primal–dual hybrid gradient algorithm
by: Zheng Qin, et al.
Published: (2025-06-01)