A Unified Kantorovich Duality for Multimarginal Optimal Transport
Yehya Cheryala, Mokhtar Z. Alaya, Salim Bouzebda

TL;DR
This paper develops a comprehensive Kantorovich duality theory for multimarginal optimal transport on general Polish spaces, extending classical duality principles and providing foundational results for statistical and machine learning applications.
Contribution
It introduces a unified duality framework for MOT on general spaces, including dual attainment and regularization of potentials, extending classical two-marginal results to the multimarginal setting.
Findings
Established duality on Polish spaces with bounded cost functions.
Proved dual attainment and primal-dual equality for general MOT.
Provided a structural foundation for stability and differentiability analysis.
Abstract
Multimarginal optimal transport (MOT) has gained increasing attention in recent years, notably due to its relevance in machine learning and statistics, where one seeks to jointly compare and align multiple probability distributions. This paper presents a unified and complete Kantorovich duality theory for MOT problem on general Polish product spaces with bounded continuous cost function. For marginal compact spaces, the duality identity is derived through a convex-analytic reformulation, that identifies the dual problem as a Fenchel-Rockafellar conjugate. We obtain dual attainment and show that optimal potentials may always be chosen in the class of -conjugate families, thereby extending classical two-marginal conjugacy principle into a genuinely multimarginal setting. In non-compact setting, where direct compactness arguments are unavailable, we recover duality via a…
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
TopicsGeometric Analysis and Curvature Flows · Markov Chains and Monte Carlo Methods · Alzheimer's disease research and treatments
