arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.01064math.PRcs.ITcs.LGmath.ITmath.STstat.TH
收藏

两个高斯混合序列间全变差距离的下界

Lower Bounds on the Total Variation Distance Between Mixtures of Two Gaussians

Northwestern University(西北大学);Halicioǧlu Data Science Institute, UC San Diego(加州大学圣地亚哥分校哈利西奥卢数据科学研究所);University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校);UC San Diego(加州大学圣地亚哥分校)

Sami Davies, Arya Mazumdar, Soumyabrata Pal, Cyrus Rashtchian

摘要:

高维高斯分布的混合分布在统计学和学习理论中得到了广泛的研究。虽然全变差距离在分布学习的样本复杂度中自然出现,但在分析上很难获得混合物的紧密下界。利用全变差距离和混合物的特征函数之间的联系,我们提供了相当紧密的函数近似。这使我们能够得到新的下界之间的全变差距离的两个组件的高斯混合物,有一个共享的协方差阵。

英文摘要:

Mixtures of high dimensional Gaussian distributions have been studied extensively in statistics and learning theory. While the total variation distance appears naturally in the sample complexity of distribution learning, it is analytically difficult to obtain tight lower bounds for mixtures. Exploiting a connection between total variation distance and the characteristic function of the mixture, we provide fairly tight functional approximations. This enables us to derive new lower bounds on the total variation distance between pairs of two-component Gaussian mixtures that have a shared covariance matrix.

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。

↑