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 2404.04240cs.LG
收藏

通过免模拟流实现动态条件最优传输

Dynamic Conditional Optimal Transport through Simulation-Free Flows

University of California, Irvine(加利福尼亚大学欧文分校)

Gavin Kerrigan, Giosue Migliorini, Padhraic Smyth

AI总结:

本文研究条件最优传输几何并推广Benamou-Brenier定理,提出一种适用于无限维贝叶斯逆问题的免模拟流条件生成建模方法,通过三角COT计划耦合分布并近似测地线路径,在多项条件生成任务上表现优异。

摘要:

我们研究了条件最优传输(COT)的几何结构,并证明了一个动态公式,该公式推广了Benamou-Brenier定理。基于这些工具,我们提出了一种用于条件生成建模的免模拟流方法。我们的方法通过三角COT计划将任意源分布与指定目标分布耦合,并通过近似由该COT计划诱导的测度测地线路径来获得条件生成模型。我们的理论和方法适用于无限维设置,使其非常适合广泛的贝叶斯逆问题。在实验中,我们证明了我们的方法在几个具有挑战性的条件生成任务上具有竞争力,包括一个无限维逆问题。

英文摘要:

We study the geometry of conditional optimal transport (COT) and prove a dynamical formulation which generalizes the Benamou-Brenier Theorem. Equipped with these tools, we propose a simulation-free flow-based method for conditional generative modeling. Our method couples an arbitrary source distribution to a specified target distribution through a triangular COT plan, and a conditional generative model is obtained by approximating the geodesic path of measures induced by this COT plan. Our theory and methods are applicable in infinite-dimensional settings, making them well suited for a wide class of Bayesian inverse problems. Empirically, we demonstrate that our method is competitive on several challenging conditional generation tasks, including an infinite-dimensional inverse problem.

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。

↑