Projective Splitting as a Warped Proximal Algorithm
Minh N. B\`ui

TL;DR
This paper demonstrates that the asynchronous block-iterative primal-dual projective splitting framework can be interpreted as a specific case of the recently developed warped proximal algorithm, providing new insights into its structure.
Contribution
It establishes a connection between the primal-dual splitting framework and warped proximal algorithms, offering a novel perspective on their relationship.
Findings
Unified view of splitting and warped proximal methods
Potential for improved algorithmic design and analysis
Enhanced understanding of convergence properties
Abstract
We show that the asynchronous block-iterative primal-dual projective splitting framework introduced by P. L. Combettes and J. Eckstein in their 2018 Math. Program. paper can be viewed as an instantiation of the recently proposed warped proximal algorithm.
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
TopicsMatrix Theory and Algorithms · Advanced Optimization Algorithms Research · Sparse and Compressive Sensing Techniques
