arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.06136math.NAcs.NAstat.CO
收藏

随机化准蒙特卡罗估计的偏度

Skewness of a randomized quasi-Monte Carlo estimate

Zexin Pan, Art B. Owen

AI总结:

本文研究随机化准蒙特卡罗估计的偏度问题,给出偏度几乎为O(1)的条件,在随机生成矩阵模型下将偏度速率提升至O(n^{-1/2+ε}),还改进了数字网质量参数t分布的概率界,解释了RQMC下普通t置信区间效果优异的原因。

摘要:

近期关于随机化准蒙特卡罗(RQMC)抽样置信区间的研究得出了一个意外结果:基于少量重复样本的普通Student t 95%置信区间效果极佳,甚至比此前被认为最优的部分bootstrap t区间更可靠。一种可能的解释是这些RQMC估计的偏度很小。本文给出了偏度为O(n^ε)(对任意ε>0成立,即“几乎O(1)”)的成立条件。在随机生成矩阵模型下,我们能以极高概率将该速率提升至O(n^{-1/2+ε})。我们还改进了素数基下数字网的质量参数t在生成矩阵随机抽样时分布的若干概率界。

英文摘要:

Some recent work on confidence intervals for randomized quasi-Monte Carlo (RQMC) sampling found a surprising result: ordinary Student $t$ 95% confidence intervals based on a modest number of replicates were seen to be very effective and even more reliable than some bootstrap $t$ intervals that were expected to be best. One potential explanation is that those RQMC estimates have small skewness. In this paper we give conditions under which the skewness is $O(n^ε)$ for any $ε>0$, so 'almost $O(1)$'. Under a random generator matrix model, we can improve this rate to $O(n^{-1/2+ε})$ with very high probability. We also improve some probabilistic bounds on the distribution of the quality parameter $t$ for a digital net in a prime base under random sampling of generator matrices.

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。

↑