On a Unified and Simplified Proof for the Ergodic Convergence Rates of PPM, PDHG and ADMM
Not on the map. Why?
Abstract (arXiv)
We present a unified viewpoint of proximal point method (PPM), primal-dual hybrid gradient (PDHG) and alternating direction method of multipliers (ADMM) for solving convex-concave primal-dual problems. This viewpoint shows the equivalence of these three algorithms upto a norm change, and it leads to a four-line simple proof of their mathcal O(1/k) ergodic rates. The simple proof technique is not limited to these three algorithms, but can also be utilized to analyze related algorithms, such as gradient descent, linearized PDHG, inexact algorithms, just to name a few.
Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 May 2023.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2024: 3; 2025: 1; 2026: 1.
5 papers.
- 2024PDHG-Unrolled Learning-to-Optimize Method for Large-Scale Linear Programmingcited by 14
- 2024Weakly Convex Regularisers for Inverse Problems: Convergence of Critical Points and Primal-Dual Optimisationcited by 12
- 2024Auto-conditioned primal-dual hybrid gradient method and alternating direction method of multiplierscited by 2
- 2025On the Relationship Between CoCoA and ADMM for Distributed Empirical Risk Minimizationcited by 0
- 2026Exploring New Frontiers in Vertical Federated Learning: the Role of Saddle Point Reformulationcited by 0
- 2026Exploring New Frontiers in Vertical Federated Learning: the Role of Saddle Point Reformulation17 Feb 2026
- 2025On the Relationship Between CoCoA and ADMM for Distributed Empirical Risk Minimization1 Feb 2025
- 2024Auto-conditioned primal-dual hybrid gradient method and alternating direction method of multipliers2 Oct 2024
- 2024PDHG-Unrolled Learning-to-Optimize Method for Large-Scale Linear Programming4 Jun 2024
- 2024Weakly Convex Regularisers for Inverse Problems: Convergence of Critical Points and Primal-Dual Optimisation1 Feb 2024