paper-with-me

홈 › Papers

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

2026-04-27 · Yumiharu Nakano arxiv

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.

📄 PDF Abstract BibTeX arXiv:2604.24226

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

The GenCol algorithm for high-dimensional optimal transport: general formulation and application to barycenters and Wasserstein splines

2022-09-19 · Gero Friesecke, Maximilian Penka

We extend the recently introduced genetic column generation algorithm for high-dimensional multi-marginal optimal transport from symmetric to general problems. We use the algorithm to calculate accurate mesh-free Wassers…

Machine Learning Optimized Approach for Parameter Selection in MESHFREE Simulations

2024-03-20 · Paulami Banerjee, Mohan Padmanabha, Chaitanya Sanghavi, Isabel Michel 외

Meshfree simulation methods are emerging as compelling alternatives to conventional mesh-based approaches, particularly in the fields of Computational Fluid Dynamics (CFD) and continuum mechanics. In this publication, we…

Active Learning

Sliced Multi-Marginal Optimal Transport

2021-02-14 · samuel cohen, Alexander Terenin, Yannik Pitcan, Brandon Amos 외

Multi-marginal optimal transport enables one to compare multiple probability measures, which increasingly finds application in multi-task learning problems. One practical limitation of multi-marginal transport is computa…

Density EstimationMulti-Task Learning

Multi-marginal optimal transport and probabilistic graphical models

2020-06-25 · Isabel Haasler, Rahul Singh, Qinsheng Zhang, Johan Karlsson 외

We study multi-marginal optimal transport problems from a probabilistic graphical model perspective. We point out an elegant connection between the two when the underlying cost for optimal transport allows a graph struct…

Bayesian Inference

Multimarginal flow matching with optimal transport potentials

2026-06-03 · Raghav Kansal, David Crair, Nghia Nguyen, Scott Pope 외 arxiv

Flow matching (FM) has emerged as a powerful framework for learning dynamic transport maps between two empirical distributions. However, less explored is the setting with intermediate observed marginals that can help con…