cs.LGMar 20, 2026

Load--Reserve Wasserstein Propagation for Isotropic Diffusion Samplers

Authors: Zicheng Lyu, Zengfeng Huang

Organizations: School of Data Science, Fudan University · Shanghai Innovation Institute

Abstract

Many Wasserstein analyses of diffusion samplers control reverse-time propagation by global stability summaries of the learned drift. These summaries can hide radial geometry: equal-height expansive regions of different width can yield different propagation costs. We give a profile-adapted propagation interface for scalar-isotropic reverse-SDE windows with certified learned-drift profiles. A certified lower radial profile is compiled into an affine-tail transportation cost: reflection coupling reduces stability to a one-dimensional slope budget, and Hardy capacity quantifies the load paid before a contractive tail reserve. The compiler yields an adapted cost, contraction rate, and retained tail slope. Score-modeling and solver residuals are treated as forcing inputs and propagate additively in the adapted Wasserstein distance. Quadratic Wasserstein error is reported only at terminal time, using the retained tail slope with tail, moment, or support information. Gaussian-smoothed denoising geometry supplies inverse-radius profiles for uniformly dissipative, bounded-amplitude, and common-covariance mixture windows. Fixed-height examples show that adverse height, even with eventual reserve, does not determine the certificate; barrier examples show that the load dependence is structural.

Figures & tables

Explore similar work

CardsList
  1. Formalizing the Sampling Design Space of Diffusion-Based Generative Models via Adaptive Solvers and Wasserstein-Bounded Timesteps

    Feb 13, 2026Sangwoo Jo, Sungjoon ChoiDiffusion Model SamplingDiffusion Sampling

  2. First-Order Stationarity of Reverse Diffusions

    Sep 25, 2026Zhifeng Chen, Chenyang Jiang, Yazhen WangDiffusion ModelsDiffusion Sampling