stat.MLJan 21, 2026

Low-Dimensional Adaptation of Rectified Flow: A Diffusion and Stochastic Localization Perspective

Authors: Saptarshi Roy, Alessandro Rinaldo, Purnamrita Sarkar

Organizations: Department of Statistics and Data Science University of Texas at Austin, TX, USA

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 \blue{end-point adapted} time-discretization scheme and with sufficiently accurate drift estimates, the RF sampler enjoys an iteration complexity of order O(k/ε)O(k/\varepsilon) (up to log factors), where ε\varepsilon is the precision in total variation distance and kk 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.

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Fast Statistical Rates for Flow Matching without Curvature Assumptions

    Jan 28, 2026Hari Krishna Sahoo, Mudit Gaur, Vaneet AggarwalRectified FlowFlow-Based Generative Modeling

  2. Low-dimensional adaptation of diffusion models: Convergence in total variation

    Jan 22, 2025Jiadong Liang, Zhihan Huang, Yuxin ChenDiffusion SamplingDiffusion Models

  3. Diffusion Models Adapt to Low-Dimensional Structure Under Flexible Coefficient Choices

    Jun 22, 2026Changxiao Cai, Yuchen Jiao, Gen LiDiffusion Model SamplingDiffusion Sampling