cs.LGFeb 13, 2026

Flow Matching from Viewpoint of Proximal Operators

Authors: Kenji Fukumizu, Wei Huang, Han Bao, Shuntuo Xu, Nisha Chandramoorthy

Organizations: The Institute of Statistical Mathematics, Japan · RIKEN AIP, Japan · Tohoku University, Japan · East China Normal University, China · 

Abstract

We discuss the dynamics of Optimal Transport Conditional Flow Matching (OT-CFM) under the manifold hypothesis, where the support of the target distribution is a low dimensional manifold. We first derive an exact proximal expression of the vector field, using an extended Brenier potential for the OT; the vector field can be expressed by a denoiser, which is presented as the proximal operator associated with the potential function. Based on this explicit proximal form of the vector field, we analyze the manifold stability for perturbations to initial points, using the Lyapunov exponents of the dynamics. By analyzing the local behavior with the tools in convex analysis, we show that the dynamics contract linearly in the perturbation of the normal directions to the manifold, while perturbations in the tangential directions are preserved; this implies the stability of the manifold structure to the perturbations. To justify the theoretical arguments on the population OT, we also establish the convergence of minibatch OT-CFM with neural network learning to population OT-CFM under regularity and stability assumptions, with rate exponents governed by the intrinsic dimension of the data manifold. Experiments on synthetic data, MNIST, and CIFAR-10 support the predicted geometric behavior.

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Sep 28, 2026

Manifold-Stable Flow Matching

Flow matching (FM) learns generative dynamics through velocity regression. Geometric FM variants commonly assume a prior supported on the data manifold, requiring geometric knowledge that is often unavailable. Without such knowledge, low regression error alone does not guarantee manifold adherence. Adherence keeps generated samples within valid configurations and is empirically associated with better task performance. We introduce manifold-stable flow matching (MSFM), which can start from an arbitrary ambient prior, not necessarily supported on the manifold. Using tools from nonlinear dynamics, namely contraction theory, MSFM combines learned tangential transport with prescribed normal contraction. The construction uses analytical projectors for known manifolds and local affine proxies estimated by principal component analysis for unknown data geometry. By implementing contraction theory in both cases of known and unknown manifolds, we guarantee manifold invariance and transverse convergence to the manifold within a desired time window (e.g., one second). We derive a family of compatible probability paths and decompose the training loss into a learnable tangential term and a normal residual. An ellipse experiment attains a mean terminal off-manifold error of order 10−610^{-6}. In Push-T robotic experiments, MSFM raises success from 74%74\% to 82%82\%. In the Robomimic Square task, success increases from 60%60\% to 72%72\%, while rotation-manifold deviation decreases from order 10−210^{-2} to 10−710^{-7}. The MSFM terminal geometric errors are controlled by the chosen numerical tolerance. These results demonstrate stronger geometric adherence and higher observed task performance, supporting prescribed normal contraction as a complement to learned generative transport.
May 12, 2026

Expected Batch Optimal Transport Plans and Consequences for Flow Matching

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 π‾k\overlineπ_{k}, obtained by averaging empirical OT plans over independent minibatches of size kk. 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 π‾k\overlineπ_{k} 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.
Aug 6, 2026

Potential Matching Optimal Transport: Continuous Normalizing Flows for Exact pp-Wasserstein Dynamics

We introduce Potential Matching Optimal Transport (PMOT), a potential-flow framework for general pp-cost optimal transport with cp(x,y)=∥x−y∥pc_p(x,y)=\|x-y\|^p. PMOT parameterizes the CNF velocity field with a scalar potential in the generalized Benamou--Brenier form for the chosen exponent pp. It trains the potential gradient with a self-induced matching loss along straight bridges determined by the model's own endpoints, while allowing flexible terminal distribution matching. Our main result establishes zero-loss exactness: under the stated regularity, exact terminal matching, and uniqueness assumptions, any zero-loss solution satisfies the generalized Benamou--Brenier optimality system and recovers the corresponding pp-optimal transport map and dynamics. On synthetic benchmarks, PMOT learns pp-specific maps that agree with the corresponding pp-matched OT references. It also remains competitive as a likelihood-based density model on high-dimensional tabular data, and an MMD-based color transformation experiment demonstrates flexible sample-based terminal matching.