arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1903.00147math.STstat.TH
收藏

无穷远处消失的连续密度函数的有限混合逼近

Approximation by finite mixtures of continuous density functions that vanish at infinity

T Tin Nguyen, Hien D Nguyen, Faicel Chamroukhi, Geoffrey J McLachlan

摘要:

在给定足够多的分量的情况下,经常引用有限混合模型可以将任何其他密度函数(pdf)近似到任意精度。不幸的是,这种近似结果的性质往往不清楚。我们证明了在$\mathcal{C}_{0}$中由PDF构造的有限混合模型可以用于在许多不同的模式中进行各种类的逼近。也就是说,我们证明了在$\mathcal{C}_{0}$中的逼近可以被一致逼近,在$\mathcal{C}_{b}$中的逼近可以在紧集上被一致逼近,以及在$\mathcal{L}_{p}$中的逼近可以关于$\mathcal{L}_{p}$被逼近,对于$p\in\left[1,\infty\right)$。此外,我们还证明了可测函数可以近似,几乎处处。

英文摘要:

Given sufficiently many components, it is often cited that finite mixture models can approximate any other probability density function (pdf) to an arbitrary degree of accuracy. Unfortunately, the nature of this approximation result is often left unclear. We prove that finite mixture models constructed from pdfs in $\mathcal{C}_{0}$ can be used to conduct approximation of various classes of approximands in a number of different modes. That is, we prove approximands in $\mathcal{C}_{0}$ can be uniformly approximated, approximands in $\mathcal{C}_{b}$ can be uniformly approximated on compact sets, and approximands in $\mathcal{L}_{p}$ can be approximated with respect to the $\mathcal{L}_{p}$, for $p\in\left[1,\infty\right)$. Furthermore, we also prove that measurable functions can be approximated, almost everywhere.

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。

↑