arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.08976stat.MLcs.LGmath.STstat.TH
收藏

核两样本检验中计算与统计的权衡:随机傅里叶特征

Computational-Statistical Trade-off in Kernel Two-Sample Testing with Random Fourier Features

Department of Statistics and Data Sciences, The University of Texas at Austin(德克萨斯大学奥斯汀分校统计与数据科学系);Department of Mathematical Sciences, KAIST(韩国科学技术院数学科学系)

Ikjun Choi, Ilmun Kim

AI总结:

本文研究了使用随机傅里叶特征近似MMD检验在计算复杂度与统计功效之间的权衡,证明通过合理选择随机特征数量可以在亚二次时间内达到与MMD检验相同的最小最大分离率。

摘要:

近年来,两样本检验方法得到了快速发展,其中最大均值差异(MMD)检验已成为处理复杂和高维数据的有效工具。尽管MMD检验在成功和广泛应用方面表现突出,但其二次时间复杂度限制了大规模分析的应用。为了解决这一问题,本文重新审视了使用随机傅里叶特征近似的MMD检验,并研究其计算-统计权衡。我们首先揭示,只有当随机特征数量趋于无穷时,近似MMD检验才能在点估计上保持一致性。随后,我们考虑检验的均匀功效,并在最小最大检验框架下研究时间-功效权衡。我们的结果表明,通过精心选择随机特征数量,可以在亚二次时间内达到与MMD检验相同的最小最大分离率。我们基于不同的分布假设(如Sobolev球内的密度)展示了这一点。理论发现通过模拟研究得到验证。

英文摘要:

Recent years have seen a surge in methods for two-sample testing, among which the Maximum Mean Discrepancy (MMD) test has emerged as an effective tool for handling complex and high-dimensional data. Despite its success and widespread adoption, the primary limitation of the MMD test has been its quadratic-time complexity, which poses challenges for large-scale analysis. While various approaches have been proposed to expedite the procedure, it has been unclear whether it is possible to attain the same power guarantee as the MMD test at sub-quadratic time cost. To fill this gap, we revisit the approximated MMD test using random Fourier features, and investigate its computational-statistical trade-off. We start by revealing that the approximated MMD test is pointwise consistent in power only when the number of random features approaches infinity. We then consider the uniform power of the test and study the time-power trade-off under the minimax testing framework. Our result shows that, by carefully choosing the number of random features, it is possible to attain the same minimax separation rates as the MMD test within sub-quadratic time. We demonstrate this point under different distributional assumptions such as densities in a Sobolev ball. Our theoretical findings are corroborated by simulation studies.

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。

↑