AI & ML
Low-Dimensional Adaptation of Rectified Flow: A Diffusion and Stochastic Localization Perspective
arXiv stat.TH0 views
arXiv:2601.15500v5 Announce Type: replace-cross Abstract: In recent years, Rectified flow (RF) has gained considerable popularity largely due to its generation efficiency and state-of-the-art performance. In this paper, we investigate how well RF automatically adapts to the intrinsic low dimensionality of the support of the target distribution to accelerate sampling. We show that, using a carefully designed end-point adapted time-discretization scheme and with sufficiently accurate drift estimates, the RF sampler enjoys an iteration complexity of order $O(k/\varepsilon)$ (up to log factors), where $\varepsilon$ is the precision in total variation distance and $k$ is the intrinsic dimension of the target distribution. In addition, we show that the denoising diffusion probabilistic model (DDPM) procedure is equivalent to a stochastic version of RF by establishing a novel connection between these processes and stochastic localization. Building on this connection, we further design a stochastic RF sampler that also adapts to the low-dimensionality of the target distribution under mild requirements on the accuracy of the drift estimates, and also with a specific time schedule. We illustrate the efficacy of newly designed time-discretization schedules with simulations on the synthetic data and text-to-image (T2I) data experiments.
Source:https://arxiv.org/abs/2601.15500PreviousLearning Robust Treatment Rules for Censored DataNextInduced replication and the assessment of models
Related posts

Enabling Real-Time AI for Scientific Instruments with GPU-Native Data Acquisition
0NVIDIA Developer Blog
The Role of Human Feedback in Improving Large Language Models
0dev.to AI
Australia Daily AI & LLM Briefing - November 20, 2026
0dev.to AI
Điểm tin AI & Mô hình Ngôn ngữ Lớn (LLMs) tại Úc - Ngày 20/11/2026
0dev.to AI
USA Today contre OpenAI : ce que demande la plainte
0dev.to AI
Get Found in Search and AI with Webpulls
0dev.to WebDev