arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.08683math.STmath.PRstat.TH
收藏

熵最优输运映射与Sinkhorn散度的极限定理

Limit Theorems for Entropic Optimal Transport Maps and the Sinkhorn Divergence

Ziv Goldfeld, Kengo Kato, Gabriel Rioux, Ritwik Sadhu

AI总结:

该研究通过分析EOT位势关于边缘分布的一二阶Hadamard可微性,结合泛函delta方法推导了EOT映射、位势及Sinkhorn散度的极限定理,还得到相关统计量的自助法一致性与渐近效率。

摘要:

我们研究熵最优输运(EOT)映射、对偶位势以及Sinkhorn散度的极限定理。所使用的核心技术工具是对EOT位势关于边缘分布的一阶与二阶Hadamard可微性分析,该分析本身可能具有独立研究价值。基于可微性结果,我们运用泛函delta方法得到了经验EOT位势与映射的中心极限定理,并利用二阶泛函delta方法建立了原假设下经验Sinkhorn散度的极限分布。在此结果基础上,我们进一步推导了Sinkhorn独立性检验统计量的原假设极限分布,并刻画了其正确阶数。由于我们的极限定理由相关映射的Hadamard可微性推导而来,作为副产品,我们还得到了经验EOT映射、位势以及Sinkhorn散度的自助法一致性与渐近效率。

英文摘要:

We study limit theorems for entropic optimal transport (EOT) maps, dual potentials, and the Sinkhorn divergence. The key technical tool we use is a first and second-order Hadamard differentiability analysis of EOT potentials with respect to the marginal distributions, which may be of independent interest. Given the differentiability results, the functional delta method is used to obtain central limit theorems for empirical EOT potentials and maps. The second-order functional delta method is leveraged to establish the limit distribution of the empirical Sinkhorn divergence under the null. Building on the latter result, we further derive the null limit distribution of the Sinkhorn independence test statistic and characterize the correct order. Since our limit theorems follow from Hadamard differentiability of the relevant maps, as a byproduct, we also obtain bootstrap consistency and asymptotic efficiency of the empirical EOT map, potentials, and Sinkhorn divergence.

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。

↑