Paperlane

no. 7 · Tuesday 3 November 2026

Continuum-marginal optimal transport: a mesh-free kernel method

Yumiharu Nakano

math.OC · v4 · 48 pp

Abstract

In this paper we study continuum-marginal optimal transport. Given a time-continuous family of probability marginals, the problem is to recover the minimum-energy velocity field whose flow reproduces every marginal. This problem is the continuum limit of the classical two-marginal Benamou-Brenier formulation, and also the deterministic limit of the Nelson problem of stochastic optimal transport. We propose a practical mesh-free solver for this problem. The weak continuity equation is embedded in a reproducing kernel Hilbert space, yielding a sample-only objective that requires no spatial discretization. The velocity is parametrized by any linear-in-parameters dictionary or neural network, and is optimized by mini-batch stochastic methods. Synthetic experiments confirm that the method achieves accurate drift recovery and marginal consistency. The same computational framework also applies to the Nelson problem.

comments
Published in Transactions on Machine Learning Research (10/2026). Reviewed on OpenReview: https://openreview.net/forum?id=1bzgCxWYpr. 48 pages, 16 figures, 14 tables
journal
Transactions on Machine Learning Research (2026)
fields
Optimization and Control, Numerical Analysis
pdf ↗ page arXiv:2604.24226 ↗