arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2511.02419math.STstat.MLstat.TH
收藏

临界阻尼朗之万扩散的Wasserstein收敛性

Wasserstein Convergence of Critically Damped Langevin Diffusions

Stanislas Strasman, Sobihan Surendran, Claire Boyer, Sylvain Le Corff, Vincent Lemaire, Antonio Ocello

AI总结:

本文提出了一种引入额外超参数控制噪声的广义临界阻尼朗之万扩散(CLD),推导了基于CLD的生成模型在Wasserstein度量下的采样误差上界,并通过离散化误差分析为超参数调整提供实用指导以提升采样性能。

摘要:

基于分数的生成模型(SGMs)在广泛的应用中实现了令人印象深刻的数据生成性能,并受益于强大的理论保证。最近,受统计力学启发的方法,特别是Hamiltonian动力学,引入了临界阻尼朗之万扩散(CLDs),通过将数据与辅助变量耦合,在扩展空间上定义扩散过程。这些方法及其相关的分数匹配和采样程序已被证明在数值上优于标准的基于扩散的采样器。在本文中,我们分析了一种广义动力学,它通过引入一个额外的超参数来控制应用于数据坐标的噪声,从而扩展了经典的CLDs,进而更好地利用扩展空间。我们进一步推导了基于CLD的生成模型在Wasserstein度量下采样误差的新颖上界。这个额外的超参数影响样本路径的平滑度,我们的离散化误差分析为其调整提供了实用指导,从而提升了采样性能。

英文摘要:

Score-based Generative Models (SGMs) have achieved impressive performance in data generation across a wide range of applications and benefit from strong theoretical guarantees. Recently, methods inspired by statistical mechanics, in particular, Hamiltonian dynamics, have introduced Critically-damped Langevin Diffusions (CLDs), which define diffusion processes on extended spaces by coupling the data with auxiliary variables. These approaches, along with their associated score-matching and sampling procedures, have been shown to outperform standard diffusion-based samplers numerically. In this paper, we analyze a generalized dynamic that extends classical CLDs by introducing an additional hyperparameter controlling the noise applied to the data coordinate, thereby better exploiting the extended space. We further derive a novel upper bound on the sampling error of CLD-based generative models in the Wasserstein metric. This additional hyperparameter influences the smoothness of sample paths, and our discretization error analysis provides practical guidance for its tuning, leading to improved sampling performance.

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。

↑