On the Convergence Rates of KNN Density Estimation

On the Convergence Rates of KNN Density Estimation
复制标题

关于KNN密度估计的收敛率

DOI:
10.1109/isit45174.2021.9518025
复制
发表时间:
2021
期刊:
2021 IEEE International Symposium on Information Theory (ISIT)
影响因子:
--
通讯作者:
L. Lai
L. Lai
中科院分区:
--
文献类型:
--
作者:
Puning Zhao;L. Lai

文献摘要

被引文献

相似文献

我们分析$ \ ell_ {1} $和$ \ ell _ {\ infty} $收敛速率的$ k $最近的邻居密度估计方法。我们的分析包括两个不同的案例,具体取决于支持集有限的情况。在第一种情况下,概率密度函数具有有界的支持,并远离零。我们表明,如果已知支持集,则在$ \ ell_ {1} $和$ \ ell _ {\ infty} $标准下,KNN密度估计是最佳的最佳选择。如果支持集未知,则$ \ ell_ {1} $错误的收敛率不受影响,而$ \ ell _ {\ infty} $错误不会收敛。在第二种情况下,概率密度函数可以接近零,并且到处都是光滑的。此外,假定黑森与密度值衰减。在这种情况下,我们的结果表明,KNN密度估计的$ \ ell _ {\ infty} $几乎是最小的。
We analyze the $\ell_{1}$ and $\ell_{\infty}$ convergence rates of $k$ nearest neighbor density estimation method. Our analysis includes two different cases depending on whether the support set is bounded or not. In the first case, the probability density function has a bounded support and is bounded away from zero. We show that kNN density estimation is minimax optimal under both $\ell_{1}$ and $\ell_{\infty}$ criteria, if the support set is known. If the support set is unknown, then the convergence rate of $\ell_{1}$ error is not affected, while $\ell_{\infty}$ error does not converge. In the second case, the probability density function can approach zero and is smooth everywhere. Moreover, the Hessian is assumed to decay with the density values. For this case, our result shows that the $\ell_{\infty}$ error of kNN density estimation is nearly minimax optimal.