The forward-backward algorithm and the normal problem
Walaa M. Moursi

TL;DR
This paper investigates the forward-backward algorithm's behavior in cases where the inclusion problem has no solution, introducing new formulas for normal solutions and the displacement map's range, supported by illustrative examples.
Contribution
It presents novel formulas for normal solutions and the displacement map range in the forward-backward algorithm when no solutions exist.
Findings
New formula for normal solutions in unsolvable cases
Range characterization of the displacement map
Illustrative examples demonstrating the theory
Abstract
The forward-backward splitting technique is a popular method for solving monotone inclusions that has applications in optimization. In this paper we explore the behaviour of the algorithm when the inclusion problem has no solution. We present a new formula to define the normal solutions using the forward-backward operator. We also provide a formula for the range of the displacement map of the forward-backward operator. Several examples illustrate our theory.
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.
