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 2210.02171math.STstat.MEstat.TH
收藏

高维两样本问题的一种均匀核技巧

A uniform kernel trick for high-dimensional two-sample problems

Javier Cárcamo, Antonio Cuevas, Luis-Alberto Rodríguez

AI总结:

本文提出一种均匀核技巧用于高维和函数型数据的两样本检验,通过涉及核距离类上确界简化核函数选择,获得检验统计量的渐近分布,并在实验中展示其优势。

摘要:

我们使用所谓“kernel trick”的合适版本来设计两样本(同质性)检验,特别聚焦于高维和函数型数据。我们的提议包含对选择合适核函数这一重要实际问题的简化。具体而言,我们应用kernel trick的均匀变体,涉及基于核的距离类内的上确界。我们获得了检验统计量(在原假设和备择假设下)的渐近分布。证明依赖于经验过程理论,结合delta方法和Hadamard(方向)可微性技术,以及底层过程的函数型Karhunen-Loève型展开。该方法论相比文献中的其他标准方法具有一些优势。我们还提供了一些实验见解,比较了我们的提议与原始基于核的方法\cite{Gretton2007}和基于能量距离的检验\cite{Szekely-Rizzo-2017}的性能。

英文摘要:

We use a suitable version of the so-called "kernel trick" to devise two-sample (homogeneity) tests, especially focussed on high-dimensional and functional data. Our proposal entails a simplification related to the important practical problem of selecting an appropriate kernel function. Specifically, we apply a uniform variant of the kernel trick which involves the supremum within a class of kernel-based distances. We obtain the asymptotic distribution (under the null and alternative hypotheses) of the test statistic. The proofs rely on empirical processes theory, combined with the delta method and Hadamard (directional) differentiability techniques, and functional Karhunen-Loève-type expansions of the underlying processes. This methodology has some advantages over other standard approaches in the literature. We also give some experimental insight into the performance of our proposal compared to the original kernel-based approach \cite{Gretton2007} and the test based on energy distances \cite{Szekely-Rizzo-2017}.

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。

↑