arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.04849stat.MLcs.LGmath.PR
收藏

推进基于分数的模型的Wasserstein收敛性分析:来自离散化与二阶加速的见解

Advancing Wasserstein Convergence Analysis of Score-Based Models: Insights from Discretization and Second-Order Acceleration

Tsinghua University(清华大学);City University of Hong Kong(香港城市大学)

Yifeng Yu, Lu Yu

AI总结:

本文针对基于分数的扩散模型,系统比较Euler离散化、指数积分器和中点随机化等方案对Wasserstein收敛性的影响,并提出基于Hessian信息和局部线性化的加速采样器,将收敛速率从标准二阶改进到一阶级别。

摘要:

基于分数的扩散模型已成为生成建模中的强大工具,但其理论基础仍未得到充分探索。本文聚焦于基于分数的扩散模型的Wasserstein收敛性分析。具体而言,我们研究了各种离散化方案的影响,包括Euler离散化、指数积分器和中点随机化方法。我们的分析对这些离散近似进行了定量比较,强调了它们对收敛行为的影响。此外,我们探索了Hessian信息可用的场景,并提出了一种基于局部线性化方法的加速采样器。我们证明,这种基于Hessian的方法实现了阶为 $\widetilde{\mathcal{O}}\left(\frac{1}{\varepsilon}\right)$ 的更快收敛速率,显著优于普通扩散模型的标准速率 $\widetilde{\mathcal{O}}\left(\frac{1}{\varepsilon^2}\right)$,其中 $\varepsilon$ 表示目标精度。

英文摘要:

Score-based diffusion models have emerged as powerful tools in generative modeling, yet their theoretical foundations remain underexplored. In this work, we focus on the Wasserstein convergence analysis of score-based diffusion models. Specifically, we investigate the impact of various discretization schemes, including Euler discretization, exponential integrators, and midpoint randomization methods. Our analysis provides a quantitative comparison of these discrete approximations, emphasizing their influence on convergence behavior. Furthermore, we explore scenarios where Hessian information is available and propose an accelerated sampler based on the local linearization method. We demonstrate that this Hessian-based approach achieves faster convergence rates of order $\widetilde{\mathcal{O}}\left(\frac{1}{\varepsilon}\right)$ significantly improving upon the standard rate $\widetilde{\mathcal{O}}\left(\frac{1}{\varepsilon^2}\right)$ of vanilla diffusion models, where $\varepsilon$ denotes the target accuracy.

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。

↑