Saved in:
Bibliographic Details
Main Authors: Liu, Peiyi, Liu, Zhaoqiang, Gu, Yiqi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.17375
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914277545213952
author Liu, Peiyi
Liu, Zhaoqiang
Gu, Yiqi
author_facet Liu, Peiyi
Liu, Zhaoqiang
Gu, Yiqi
contents In this paper, we develop a class of samplers for the diffusion model using the operator-splitting technique. The linear drift term and the nonlinear score-driven drift of the probability flow ordinary differential equation are split and applied by flow maps alternatively. Moreover, we conduct detailed analyses for the second-order sampler, establishing a non-asymptotic total variation distance error bound of order $O(d/T^2+\sqrt{d}\varepsilon_{\mathrm{score}}+d\varepsilon_{\mathrm{Jac}})$, where $d$ is the data dimension; $T$ is the number of sampling steps; $\varepsilon_{\mathrm{score}}$ and $\varepsilon_{\mathrm{Jac}}$ measure the discrepancy between the actual score function and learned score function. Our bound is sharper than existing works, yielding bounds of $O(d^p/T^2)$ with some $p>1$ for specific second-order samplers. Numerical experiments on a two-dimensional synthetic dataset corroborate the established quadratic dependence on the step size $1/T$ in the error bound.
format Preprint
id arxiv_https___arxiv_org_abs_2601_17375
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Operator splitting based diffusion samplers and improved convergence analysis
Liu, Peiyi
Liu, Zhaoqiang
Gu, Yiqi
Numerical Analysis
In this paper, we develop a class of samplers for the diffusion model using the operator-splitting technique. The linear drift term and the nonlinear score-driven drift of the probability flow ordinary differential equation are split and applied by flow maps alternatively. Moreover, we conduct detailed analyses for the second-order sampler, establishing a non-asymptotic total variation distance error bound of order $O(d/T^2+\sqrt{d}\varepsilon_{\mathrm{score}}+d\varepsilon_{\mathrm{Jac}})$, where $d$ is the data dimension; $T$ is the number of sampling steps; $\varepsilon_{\mathrm{score}}$ and $\varepsilon_{\mathrm{Jac}}$ measure the discrepancy between the actual score function and learned score function. Our bound is sharper than existing works, yielding bounds of $O(d^p/T^2)$ with some $p>1$ for specific second-order samplers. Numerical experiments on a two-dimensional synthetic dataset corroborate the established quadratic dependence on the step size $1/T$ in the error bound.
title Operator splitting based diffusion samplers and improved convergence analysis
topic Numerical Analysis
url https://arxiv.org/abs/2601.17375