arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.23151cs.LG
收藏

面向流形的扰动用于约束生成建模

Manifold-Aware Perturbations for Constrained Generative Modeling

Department of XXX, University of YYY, Location, Country(YYY大学XXX系);School of ZZZ, Institute of WWW, Location, Country(WWW研究所ZZZ学院);Department of Mathematics, Emory University, Atlanta, Georgia, USA(埃默里大学数学系)

Katherine Keegan, Lars Ruthotto

AI总结:

本文提出了一种面向流形的扰动方法,用于改进约束生成模型的数据分布恢复与稳定采样。

摘要:

生成模型在各种应用中取得了广泛应用。然而,它们在建模受等式约束的分布时会遇到固有的数学限制,这在科学领域中经常出现。在本工作中,我们开发了一种计算成本低、数学上合理且高度灵活的分布修改方法,以应对已知的等式约束生成模型中的问题。我们提出了一种在约束意识下扰动数据分布的方法,使得新分布的支持集与 ambient 空间维度匹配,同时隐式地融入底层流形几何。通过理论分析和在多个代表性任务上的实验证据,我们证明了我们的方法能够一致地实现数据分布恢复和稳定采样,无论是扩散模型还是归一化流。

英文摘要:

Generative models have enjoyed widespread success in a variety of applications. However, they encounter inherent mathematical limitations in modeling distributions where samples are constrained by equalities, as is frequently the setting in scientific domains. In this work, we develop a computationally cheap, mathematically justified, and highly flexible distributional modification for combating known pitfalls in equality-constrained generative models. We propose perturbing the data distribution in a constraint-aware way such that the new distribution has support matching the ambient space dimension while still implicitly incorporating underlying manifold geometry. Through theoretical analyses and empirical evidence on several representative tasks, we illustrate that our approach consistently enables data distribution recovery and stable sampling with both diffusion models and normalizing flows.

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。

↑