paper-with-me

홈 › Papers

Flow Matching from Viewpoint of Proximal Operators

2026-02-13 · Kenji Fukumizu, Wei Huang, Han Bao, Shuntuo Xu, Nisha Chandramoorthy arxiv

We reformulate Optimal Transport Conditional Flow Matching (OT-CFM), a class of dynamical generative models, showing that it admits an exact proximal formulation via an extended Brenier potential, without assuming that the target distribution has a density. In particular, the mapping to recover the target point is exactly given by a proximal operator, which yields an explicit proximal expression of the vector field. We also discuss the convergence of minibatch OT-CFM to the population formulation as the batch size increases. Finally, using second epi-derivatives of convex potentials, we prove that, for manifold-supported targets, OT-CFM is terminally normally hyperbolic: after time rescaling, the dynamics contracts exponentially in directions normal to the data manifold while remaining neutral along tangential directions.

📄 PDF Abstract BibTeX arXiv:2602.12683

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Proximal Residual Flows for Bayesian Inverse Problems

2022-11-30 · Johannes Hertrich

Normalizing flows are a powerful tool for generative modelling, density estimation and posterior reconstruction in Bayesian inverse problems. In this paper, we introduce proximal residual flows, a new architecture of nor…

Density Estimation

Combining Wasserstein-1 and Wasserstein-2 proximals: robust manifold learning via well-posed generative flows

2024-07-16 · Hyemin Gu, Markos A. Katsoulakis, Luc Rey-Bellet, Benjamin J. Zhang

We formulate well-posed continuous-time generative flows for learning distributions that are supported on low-dimensional manifolds through Wasserstein proximal regularizations of $f$-divergences. Wasserstein-1 proximal …

What's in a Prior? Learned Proximal Networks for Inverse Problems

2023-10-22 · Zhenghan Fang, Sam Buchanan, Jeremias Sulam

Proximal operators are ubiquitous in inverse problems, commonly appearing as part of algorithmic strategies to regularize problems that are otherwise ill-posed. Modern deep learning models have been brought to bear for t…

General Proximal Flow Networks

2026-02-28 · Alexander Strunk, Roland Assam arxiv

This paper introduces General Proximal Flow Networks (GPFNs), a generalization of Bayesian Flow Networks that broadens the class of admissible belief-update operators. In Bayesian Flow Networks, each update step is a Bay…

FlowPRO: Reward-Free Reinforced Fine-Tuning of Flow-Matching VLAs via Proximalized Preference Optimization

2026-06-03 · Yihao Wu, He Zhang, Junbo Tan, Xueqian Wang 외 arxiv

Post-training Vision-Language-Action (VLA) models into policies that can be reliably deployed on real robots remains a major bottleneck. SFT and DAgger exploit failure signals only indirectly, and reward-based RL is bott…