paper-with-me

Papers

Dynamic Conditional Optimal Transport through Simulation-Free Flows

2024-04-05 · Gavin Kerrigan, Giosue Migliorini, Padhraic Smyth

We study the geometry of conditional optimal transport (COT) and prove a dynamical formulation which generalizes the Benamou-Brenier Theorem. Equipped with these tools, we propose a simulation-free flow-based method for conditional generative modeling. Our method couples an arbitrary source distribution to a specified target distribution through a triangular COT plan, and a conditional generative model is obtained by approximating the geodesic path of measures induced by this COT plan. Our theory and methods are applicable in infinite-dimensional settings, making them well suited for a wide class of Bayesian inverse problems. Empirically, we demonstrate that our method is competitive on several challenging conditional generation tasks, including an infinite-dimensional inverse problem.

📄 PDF Abstract BibTeX arXiv:2404.04240

Code (1)

gavinkerrigan/cot_fm 공식 구현 jax

Tasks

Image-to-Image Translation

Similar Papers 제목 키워드 기반

Simulation-free Unbalanced Dynamic Optimal Transport with General Growth Penalty

2026-09-04 · Junda Ying, Yuxuan Wang, Bowen Yang, Peijie Zhou 외 arxiv

Inferring cellular dynamics from unpaired single-cell snapshots requires modeling both state transitions and population growth or death. Unbalanced dynamic optimal transport (UDOT) addresses this by penalizing growth alo…

MST-Direct at Scale: Multivariate and Conditional Geostatistical Simulation via Sinkhorn Optimal Transport

2026-05-26 · Tcharlies Bachmann Schmitz arxiv

This paper extends MST-Direct, a Matching-via-Sinkhorn-Transport approach for multivariate geostatistical simulation, from the original bivariate, unconditional, small-grid formulation to multivariate, conditional, and l…

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…

Improving and generalizing flow-based generative models with minibatch optimal transport

2023-02-01 · Alexander Tong, Kilian Fatras, Nikolay Malkin, Guillaume Huguet 외

Continuous normalizing flows (CNFs) are an attractive generative modeling technique, but they have been held back by limitations in their simulation-based maximum likelihood training. We introduce the generalized conditi…

Conditional simulation via entropic optimal transport: Toward non-parametric estimation of conditional Brenier maps

2024-11-11 · Ricardo Baptista, Aram-Alexandre Pooladian, Michael Brennan, Youssef Marzouk 외

Conditional simulation is a fundamental task in statistical modeling: Generate samples from the conditionals given finitely many data points from a joint distribution. One promising approach is to construct conditional B…

Bayesian Inference