From Optimal Transport to Discrepancy
Sebastian Neumayer () and
Gabriele Steidl ()
Additional contact information
Sebastian Neumayer: TU Berlin, Institute of Mathematics
Gabriele Steidl: TU Berlin, Institute of Mathematics
Chapter 50 in Handbook of Mathematical Models and Algorithms in Computer Vision and Imaging, 2023, pp 1791-1826 from Springer
Abstract:
Abstract A common way to quantify the “distance” between measures is via their discrepancy, also known as maximum mean discrepancy (MMD). Discrepancies are related to Sinkhorn divergences Sε with appropriate cost functions as ε →∞. In the opposite direction, if ε → 0, Sinkhorn divergences approach another important distance between measures, namely, the Wasserstein distance or more generally optimal transport “distance.” In this chapter, we investigate the limiting process for arbitrary measures on compact sets and Lipschitz continuous cost functions. In particular, we are interested in the behavior of the corresponding optimal potentials φ ̂ ε $$\hat \varphi _\varepsilon $$ , ψ ̂ ε $$\hat \psi _\varepsilon $$ , and φ ̂ K $$\hat \varphi _K$$ appearing in the dual formulation of the Sinkhorn divergences and discrepancies, respectively. While part of the results is known, we provide rigorous proofs for some relations which we have not found in this generality in the literature. Finally, we demonstrate the limiting process by numerical examples and show the behavior of the distances when used for the approximation of measures by point measures in a process called dithering.
Keywords: Discrepancies; Duality; Interpolation; Optimal transport; Sinkhorn divergence (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:
There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-030-98661-2_95
Ordering information: This item can be ordered from
http://www.springer.com/9783030986612
DOI: 10.1007/978-3-030-98661-2_95
Access Statistics for this chapter
More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().