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 1508.00655math.STcs.AIcs.ITcs.LGmath.ITstat.MLstat.TH
收藏

基于核和距离的高维双样本检验的自适应性和计算-统计权衡

Adaptivity and Computation-Statistics Tradeoffs for Kernel and Distance based High Dimensional Two Sample Testing

Carnegie Mellon University(卡内基梅隆大学)

Aaditya Ramdas, Sashank J. Reddi, Barnabas Poczos, Aarti Singh, Larry Wasserman

摘要:

非参数双样本检验是一个决策理论问题,涉及识别两个随机变量之间的差异,而不对它们的潜在分布进行参数假设。我们将最常见的设置称为均值差替代(MDA),仅用于测试第一时刻的差异,以及一般差异替代(GDA),这是关于测试分布中的任何差异。大量的检验统计量已经提出了这两种设置。本文将三种统计方法--Hotelling t检验的高维变量、基于再生核希尔伯特空间的统计方法和基于两两距离的能量统计方法联系起来。我们提出这样一个问题:当未知分布的平均值不同时,与MDA的专门测试相比,GDA的流行的基于内核和距离的测试有多大的统计能力?我们正式表征了GDA流行测试的功效,例如具有高斯核的最大平均差异(gMMD)和具有高维MDA机制中的欧几里得范数(eED)的能量距离的带宽相关变体。一些实际上重要的属性包括(a)eED和gMMD具有渐近相等的功效;此外,它们享受免费的午餐,因为虽然它们对于GDA是额外一致的,但它们也具有与MDA的专用高维t检验变体相同的功效。所有这些检验都是渐近最优的(包括匹配常数),(b)gMMD的功率与内核带宽无关,只要它大于中值启发式做出的选择,(c)对于这些测试的线性时间、次二次时间和二次时间版本,存在清晰且平滑的计算统计权衡,更多的计算导致更高的功率。

英文摘要:

Nonparametric two sample testing is a decision theoretic problem that involves identifying differences between two random variables without making parametric assumptions about their underlying distributions. We refer to the most common settings as mean difference alternatives (MDA), for testing differences only in first moments, and general difference alternatives (GDA), which is about testing for any difference in distributions. A large number of test statistics have been proposed for both these settings. This paper connects three classes of statistics - high dimensional variants of Hotelling's t-test, statistics based on Reproducing Kernel Hilbert Spaces, and energy statistics based on pairwise distances. We ask the question: how much statistical power do popular kernel and distance based tests for GDA have when the unknown distributions differ in their means, compared to specialized tests for MDA? We formally characterize the power of popular tests for GDA like the Maximum Mean Discrepancy with the Gaussian kernel (gMMD) and bandwidth-dependent variants of the Energy Distance with the Euclidean norm (eED) in the high-dimensional MDA regime. Some practically important properties include (a) eED and gMMD have asymptotically equal power; furthermore they enjoy a free lunch because, while they are additionally consistent for GDA, they also have the same power as specialized high-dimensional t-test variants for MDA. All these tests are asymptotically optimal (including matching constants) under MDA for spherical covariances, according to simple lower bounds, (b) The power of gMMD is independent of the kernel bandwidth, as long as it is larger than the choice made by the median heuristic, (c) There is a clear and smooth computation-statistics tradeoff for linear-time, subquadratic-time and quadratic-time versions of these tests, with more computation resulting in higher power.

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。

↑