arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.09665math.STmath.OCmath.PRstat.MLstat.TH
收藏

采样与扩散模型的新算法

New algorithms for sampling and diffusion models

Xicheng Zhang

AI总结:

本研究受扩散生成模型逆扩散过程启发,基于随机微分方程提出新型采样与扩散生成模型算法,推导显式收敛速率与无维粒子近似收敛结果,实验验证有效,且采样无需目标分布密度正则性假设,还可应用于优化问题。

摘要:

基于随机微分方程理论,我们提出了一种针对已知分布的新型采样方法,以及一种适用于分布未知场景的扩散生成模型新算法。该方法的灵感来源于扩散生成模型中广泛采用的逆扩散过程概念。此外,我们基于光滑常微分方程(ODE)流推导了显式收敛速率。针对扩散生成模型与采样任务,我们建立了不依赖维度的粒子近似收敛结果。数值实验验证了我们方法的有效性。值得注意的是,与传统的Langevin方法不同,我们的采样方法无需对目标分布的密度函数做任何正则性假设。此外,我们还将该方法应用于优化问题。

英文摘要:

Drawing from the theory of stochastic differential equations, we introduce a novel sampling method for known distributions and a new algorithm for diffusion generative models with unknown distributions. Our approach is inspired by the concept of the reverse diffusion process, widely adopted in diffusion generative models. Additionally, we derive the explicit convergence rate based on the smooth ODE flow. For diffusion generative models and sampling, we establish a dimension-free particle approximation convergence result. Numerical experiments demonstrate the effectiveness of our method. Notably, unlike the traditional Langevin method, our sampling method does not require any regularity assumptions about the density function of the target distribution. Furthermore, we also apply our method to optimization problems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑