# Expected Batch Optimal Transport Plans and Consequences for Flow Matching

arXiv: https://arxiv.org/abs/2605.12174 · HTML: https://mlsanity.com/paper/2605.12174/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 2 of its 39 references that are in the map.
- First posted on arXiv 12 May 2026.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 2 of 2)

- [Minibatch optimal transport distances; analysis and applications](https://mlsanity.com/paper/2101.01792/) (2021)
- [Tessellations of Semi-Discrete Flow Matching](https://mlsanity.com/paper/2605.07513/) (2026)

## Built on by (most cited first, 6 of 6)

- [One-Sided Quantile Coupling for Flow Matching](https://mlsanity.com/paper/2608.00978/) (2026)
- [Limit Points of Reflow with Minibatch Optimal Transport](https://mlsanity.com/paper/2608.07042/) (2026)
- [CyFM: Cylindrical Optimal Transport for Few-Step Complex-Valued Flow Matching](https://mlsanity.com/paper/2609.14171/) (2026)
- [One-Step Generative Modeling via Training Dynamics Action](https://mlsanity.com/paper/2610.00518/) (2026)
- [Global Transport Couplings for Classifier-Free Guided Flows](https://mlsanity.com/paper/2610.07555/) (2026)
- [Scaling Online Optimal Transport Minibatches for Flow Matching](https://mlsanity.com/paper/2610.18838/) (2026)

## Abstract (arXiv)

Solving optimal transport (OT) on random minibatches is a common surrogate for exact OT in large-scale learning. In flow matching (FM), this surrogate is used to obtain OT-like couplings that can straighten probability paths and reduce numerical integration cost. Yet, the population-level coupling induced by repeated minibatch OT remains only partially understood. We formalize this coupling as the expected batch OT plan overlineπk, obtained by averaging empirical OT plans over independent minibatches of size k. We then establish its large-batch consistency and, in the semidiscrete case relevant to generative modeling, derive rates for both the transport-cost bias and the convergence of overlineπk to the OT plan. For FM, this yields a population coupling whose induced velocity field is regular enough to define a unique flow from the source to the discrete target. We finally quantify how OT batch size interacts with numerical integration in a tractable two-atom model and in synthetic and image experiments.