Fast Sampling of Diffusion Models with Exponential Integrator
Qinsheng Zhang Georgia Institute of Technology、Yongxin Chen Georgia Institute of Technology
Abstract
The past few years have witnessed the great success of Diffusion models (DMs) in generating high-fidelity samples in generative modeling tasks. A major limitation of the DM is its notoriously slow sampling procedure which normally requires hundreds to thousands of time discretization steps of the learned diffusion process to reach the desired accuracy. Our goal is to develop a fast sampling method for DMs with fewer steps while retaining high sample quality. To this end, we systematically analyze the sampling procedure in DMs and identify key factors that affect the sample quality, among which the method of discretization is most crucial. By carefully examining the learned diffusion process, we propose Diffusion Exponential Integrator Sampler (DEIS). It is based on the Exponential Integrator designed for discretizing ordinary differential equations (ODEs) and leverages a semilinear structure of the learned diffusion process to reduce the discretization error. The proposed method can be applied to any DMs and can generate high-fidelity samples in as few as 10 steps. Moreover, by directly using pre-trained DMs, we achieve state-of-art sampling performance when the number of score fun
中文速览
扩散模型（Diffusion Models）生成质量出色，却因需要成百上千步的迭代采样而极其耗时，如何用极少的步数保持高质量采样是亟待解决的难题。作者从误差来源入手系统分析了采样过程，发现离散化方案对采样质量影响最为关键，并注意到扩散模型的概率流ODE具有"半线性"（semilinear）结构——线性部分可以精确处理，非线性部分才是近似的来源。基于此，他们借鉴常微分方程领域的指数积分器（Exponential Integrator）思想，提出了扩散指数积分采样器（DEIS，Diffusion Exponential Integrator Sampler），通过高阶多项式拟合或龙格-库塔方法进一步压缩离散化误差，且可直接套用任何已训练好的扩散模型无需重新训练。在CIFAR10基准上，DEIS仅用10次网络评估就达到FID 4.17、20次评估达到FID 2.86，大幅超越此前方法，为扩散模型在实时或资源受限场景下的实际部署铺平了道路。
原文 arXiv:2204.13902;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2204.13902v4