Hugging Face Trending Papers

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

Read the original on Hugging Face Trending Papers →

We introduce Potential Matching Optimal Transport (PMOT), a potential-flow framework for general $p$-cost optimal transport with $c_p(x,y)=\|x-y\|^p$. PMOT parameterizes the CNF velocity field with a scalar potential in the generalized Benamou--Brenier form for the chosen exponent $p$.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv Machine Learning
Aug 7

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

arXiv:2608. 05666v1 Announce Type: new Abstract: We introduce Potential Matching Optimal Transport (PMOT), a potential-flow framework for general $p$-cost optimal transport with $c_p(x,y)=\|x-y\|^p$.

By Lishuo Zhang (School of Mathematical Sciences, Shanghai Jiao Tong University), Ruizhi Huang (School of Mathematical Sciences, Shanghai Jiao Tong University), Yang Yu (School of Mathematical Sciences, Shanghai Jiao Tong University), Lei Li (School of Mathematical Sciences, Shanghai Jiao Tong University, Institute of Natural Sciences, MOE-LSC, Shanghai Jiao Tong University)
arXiv Machine Learning
Jun 25

Entropy-Controlled Flow Matching

arXiv:2602. 22265v2 Announce Type: replace Abstract: Modern vision generators transport a base distribution to data through time-indexed measures, implemented as deterministic flows (ODEs) or stochastic diffusions (SDEs).

By Chika Maduabuchi
arXiv Machine Learning
Aug 4

Beckmann Transport Models: From Autonomous Flows to One-Step Maps

arXiv:2608. 01692v1 Announce Type: new Abstract: We propose an instantiation of flow matching that relies on a time-independent velocity field (an \emph{autonomous flow}) to exactly map between two distributions, so long as the target is singular, i.

By Lee Cheuk-Kit, Florentin Coeurdoux, Peter Potaptchik, Yilun Du, Michael Samuel Albergo, Eric Vanden-Eijnden
arXiv Machine Learning
Jul 21

Twisted Schr\"odinger Bridge Matching

arXiv:2607. 16987v1 Announce Type: cross Abstract: Over the past few years, diffusion-based Schr\"odinger bridge models have been proposed to approximate optimal transport dynamics between two prescribed boundary distributions, with successful applications to generative modeling.

By Maxence Noble, Marie Scheid, Yazid Janati, Eric Moulines, Alain Durmus
arXiv AI
Jun 24

The Geometry Behind Diffusion and Flow Matching: Gradient Flows and Geodesics in Wasserstein Space

arXiv:2606. 24157v1 Announce Type: new Abstract: The space $\mathcal{P}_2(\mathbb{R}^d$) of probability measures with finite second moment carries a natural geometry: the quadratic Wasserstein distance W_2 makes it a complete metric space and, following Otto, a (formal) Riemannian manifold whose geodesics are the optimal-transport interpolations.

By Yian Yao, Weiwei Zhang
Hugging Face Trending Papers
Jun 29

The Fundamental Limits of Valid Transport Map Estimation

Many modern generative modeling methods, including diffusion models, normalizing flows, and flow matching, estimate transport maps or plans between distributions without explicitly targeting an optimal transport (OT) map. In applications like generative modeling, the transport cost itself is irrelevant, and this makes it natural to target maps which are more tractable from either a statistical or computational standpoint.