Free complete Wasserstein algebras
Radu Mardare, Prakash Panangaden, and Gordon D. Plotkin

TL;DR
This paper develops an algebraic framework for Wasserstein distances on complete metric spaces, connecting probabilistic measures with algebraic structures to facilitate reasoning about effects in programming languages.
Contribution
It introduces axioms for Wasserstein-algebraic structures parametrized by p and characterizes their free complete algebras as Radon probability measures with Wasserstein metrics.
Findings
Identifies axioms for Wasserstein algebras over metric spaces.
Characterizes free complete Wasserstein algebras as Radon probability measures.
Links algebraic structures with probabilistic metrics in programming semantics.
Abstract
We present an algebraic account of the Wasserstein distances on complete metric spaces, for . This is part of a program of a quantitative algebraic theory of effects in programming languages. In particular, we give axioms, parametric in , for algebras over metric spaces equipped with probabilistic choice operations. The axioms say that the operations form a barycentric algebra and that the metric satisfies a property typical of the Wasserstein distance . We show that the free complete such algebra over a complete metric space is that of the Radon probability measures with finite moments of order , equipped with the Wasserstein distance as metric and with the usual binary convex sums as operations.
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 Banach Space Theory · Commutative Algebra and Its Applications · Advanced Topology and Set Theory
