跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.23617 · v1

Error accumulation in reverse diffusion with an imperfect score: beyond path-space analyses

首次提交 2026-11-18 07:18
版本更新 2026-11-18 07:18
雷达观测 2026-11-19 19:08
arXiv ↗PDF ↗

摘要

Diffusion modeling is a popular method of sampling from a complex, high-dimensional distribution pp using learned approximations of its (noised) score functions. Generating a single sample requires simulating the reverse diffusion process, which requires many queries to the learned scores. Thus, a priori, the learning errors can easily compound. Indeed, in existing theoretical analyses, the sampling error (as measured in total variation distance to pp) accumulates polynomially with the horizon of the stochastic process. This is a consequence of bounding the error of the output law by the error of the law of the entire reverse diffusion path. In this paper, we demonstrate that by circumventing the "path-space" analysis, the error accumulation of the diffusion sampler can be mitigated when pp satisfies a Poincaré inequality. Moreover, we achieve this result as a special case of a broader framework that applies to any distribution pp, but relaxes the error metric from total variation distance to a weaker metric capturing all sample statistics that do not "witness" the multimodality of pp. We then zoom out from analyzing the diffusion sampler to the information-theoretic question: given a learned score with some error bound, how accurately can we identify pp? We show that, for any given bound on the Poincaré constant of pp, the diffusion sampler already nearly achieves optimal total variation error.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-18 07:18 · 最新观测版本

Error accumulation in reverse diffusion with an imperfect score: beyond path-space analyses

Diffusion modeling is a popular method of sampling from a complex, high-dimensional distribution pp using learned approximations of its (noised) score functions. Generating a single sample requires simulating the reverse diffusion process, which requires many queries to the learned scores. Thus, a priori, the learning errors can easily compound. Indeed, in existing theoretical analyses, the sampling error (as measured in total variation distance to pp) accumulates polynomially with the horizon of the stochastic process. This is a consequence of bounding the error of the output law by the error of the law of the entire reverse diffusion path. In this paper, we demonstrate that by circumventing the "path-space" analysis, the error accumulation of the diffusion sampler can be mitigated when pp satisfies a Poincaré inequality. Moreover, we achieve this result as a special case of a broader framework that applies to any distribution pp, but relaxes the error metric from total variation distance to a weaker metric capturing all sample statistics that do not "witness" the multimodality of pp. We then zoom out from analyzing the diffusion sampler to the information-theoretic question: given a learned score with some error bound, how accurately can we identify pp? We show that, for any given bound on the Poincaré constant of pp, the diffusion sampler already nearly achieves optimal total variation error.

查看此版本解读 →查看此版本原文 ↗