Statistics > Machine Learning
Title:On sparsity, extremal structure, and monotonicity properties of Wasserstein and Gromov-Wasserstein optimal transport plans
Abstract:This note gives a self-contained overview of some key properties of the Gromov-Wasserstein (GW) distance, compared with the standard linear optimal transport (OT) framework. More specifically, I explore the following questions: are GW optimal transport plans sparse? under what conditions does there exist an optimal plan supported on a permutation? do optimal plans satisfy a form of cyclical monotonicity? In particular, I present the conditionally negative/positive definite (CND/CPD) properties and show that, when they hold, there exist GW optimal plans that are sparse and supported on a permutation. In the last section, I also give examples where no permutation is optimal when the CND or CPD assumption is dropped.
| Subjects: | Machine Learning (stat.ML) ; Machine Learning (cs.LG) |
|---|---|
| Cite as: | arXiv:2602.16265 [stat.ML] |
| (or arXiv:2602.16265v3 [stat.ML] for this version) | |
| https://doi.org/10.48550/arXiv.2602.16265 arXiv-issued DOI via DataCite |
Submission history
Access Paper:
Current browse context:
References & Citations
- Google Scholar
- Semantic Scholar
BibTeX formatted citation
Bookmark
Bibliographic and Citation Tools
Code, Data and Media Associated with this Article
Demos
Recommenders and Search Tools
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.