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 2602.08579cs.LG
收藏

通过正向随机偏微分方程建模扩散模型中的分数近似误差

Modeling Score Approximation Errors in Diffusion Models via Forward SPDEs

SNU(全南大学)

Junsu Seo

AI总结:

本文通过正向SPDE框架建模扩散模型中的分数近似误差,提出基于二次变分的评估度量,并探讨生成模型的鲁棒性与计算效率。

摘要:

本研究通过将分数估计误差视为驱动福克-普朗克方程的随机源,探讨了基于分数的生成模型(SGMs)的动力学。不同于以粒子为中心的SDE分析,我们采用SPDE框架来建模在随机漂移扰动下概率密度场的演化。在简化设定下,我们利用该框架通过几何稳定性与位移凸性的角度解释生成模型的鲁棒性。此外,我们引入了一个候选评估度量,该度量源自SPDE解在径向测试函数上的二次变分。初步观察表明,该度量仅使用采样轨迹的前10%即可保持有效性,显示出潜在的计算效率。

英文摘要:

This study investigates the dynamics of Score-based Generative Models (SGMs) by treating the score estimation error as a stochastic source driving the Fokker-Planck equation. Departing from particle-centric SDE analyses, we employ an SPDE framework to model the evolution of the probability density field under stochastic drift perturbations. Under a simplified setting, we utilize this framework to interpret the robustness of generative models through the lens of geometric stability and displacement convexity. Furthermore, we introduce a candidate evaluation metric derived from the quadratic variation of the SPDE solution projected onto a radial test function. Preliminary observations suggest that this metric remains effective using only the initial 10% of the sampling trajectory, indicating a potential for computational efficiency.

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。

↑