On the pointwise iteration-complexity of a dynamic regularized ADMM with over-relaxation stepsize
M.L.N. Goncalves

TL;DR
This paper extends the pointwise iteration-complexity analysis of a dynamic regularized ADMM to a broader stepsize domain, including over-relaxation, by interpreting it within a hybrid proximal extragradient framework.
Contribution
It broadens the stepsize domain for the complexity analysis of ADMM, allowing stepsizes in (0,2), and provides a new interpretation via a hybrid proximal extragradient framework.
Findings
Allowed stepsize in (0,2) for ADMM complexity analysis
Unified analysis framework using hybrid proximal extragradient method
Enhanced understanding of ADMM iteration complexity
Abstract
In this paper, we extend the improved pointwise iteration-complexity result of a dynamic regularized alternating direction method of multipliers (ADMM) for a new stepsize domain. In this complexity analysis, the stepsize parameter can even be chosen in the interval instead of interval . As usual, our analysis is established by interpreting this ADMM variant as an instance of a hybrid proximal extragradient framework applied to a specific monotone inclusion problem.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Numerical Methods in Computational Mathematics · Model Reduction and Neural Networks · Matrix Theory and Algorithms
