paper-with-me

홈 › Papers

Statistical Properties of Rectified Flow

2025-11-05 · Gonzalo Mena, Arun Kumar Kuchibhotla, Larry Wasserman arxiv

Rectified flow (Liu et al., 2022; Liu, 2022; Wu et al., 2023) is a method for defining a transport map between two distributions, and enjoys popularity in machine learning, although theoretical results supporting the validity of these methods are scant. The rectified flow can be regarded as an approximation to optimal transport, but in contrast to other transport methods that require optimization over a function space, computing the rectified flow only requires standard statistical tools such as regression or density estimation, which we leverage to develop empirical versions of transport maps. We study some structural properties of the rectified flow, including existence, uniqueness, and regularity, as well as the related statistical properties, such as rates of convergence and central limit theorems, for some selected estimators. To do so, we analyze the bounded and unbounded cases separately as each presents unique challenges. In both cases, we are able to establish convergence at faster rates than those for the usual nonparametric regression and density estimation.

📄 PDF Abstract BibTeX arXiv:2511.03193

Code (0)

등록된 구현이 없습니다.

Tasks

Density Estimation

Similar Papers 제목 키워드 기반

On the Relation between Rectified Flows and Optimal Transport

2025-05-26 · Johannes Hertrich, Antonin Chambolle, Julie Delon

This paper investigates the connections between rectified flows, flow matching, and optimal transport. Flow matching is a recent approach to learning generative models by estimating velocity fields that guide transformat…

Relation

Text-to-Image Rectified Flow as Plug-and-Play Priors

2024-06-05 · Xiaofeng Yang, Cheng Chen, Xulei Yang, Fayao Liu 외

Large-scale diffusion models have achieved remarkable performance in generative tasks. Beyond their initial training applications, these models have proven their ability to function as versatile plug-and-play priors. For…

3D GenerationText to 3D

TraFlow: Trajectory Distillation on Pre-Trained Rectified Flow

2025-02-24 · Zhangkai Wu, Xuhui Fan, Hongyu Wu, Longbing Cao

Majorities of distillation methods on pre-trained diffusion models or on pre-trained rectified flow, focus on either the distillation outputs or the trajectories between random noises and clean images to speed up sample …

From Diffusion to Flow: Efficient Motion Generation in MotionGPT3

2026-03-23 · Jaymin Ban, JiHong Jeon, SangYeop Jeong arxiv

Recent text-driven motion generation methods span both discrete token-based approaches and continuous-latent formulations. MotionGPT3 exemplifies the latter paradigm, combining a learned continuous motion latent space wi…

Audio Generation

AReUReDi: Annealed Rectified Updates for Refining Discrete Flows with Multi-Objective Guidance

2025-09-30 · Tong Chen, Yinuo Zhang, Pranam Chatterjee arxiv

Designing sequences that satisfy multiple, often conflicting, objectives is a central challenge in therapeutic and biomolecular engineering. Existing generative frameworks largely operate in continuous spaces with single…