arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1404.2298math.STstat.TH
收藏

对数凹密度估计的全局收敛速度

Global rates of convergence in log-concave density estimation

Arlene K. H. Kim, Richard J. Samworth

摘要:

$\mathbb{R}^d$上对数凹密度的估计是形状约束下非参数推断领域的一个中心问题。本文研究了对数凹密度估计在全局损失函数下的性能,并采用了极大极小方法。我们首先表明,没有统计程序的基础上的样本大小$n$可以估计一个对数凹密度的平方Hellinger损失函数的上确界风险小于$n^{-4/5}$时,$d=1$,为了$n^{-2/(d+1)}$时,$d \geq 2$。特别是,这揭示了一种意义,其中,当$d \geq 3$,对数凹密度估计是从根本上更具挑战性的密度估计与两个有界导数(一个问题,它已被比较)。其次,我们证明了对于$d \leq 3$,一类对数凹密度的Hellinger $ε$ -包围熵具有小的平均值和协方差矩阵接近恒等式,其增长类似于$\max\{ε^{-d/2},ε^{-(d-1)}\}$(当$d=2$时达到对数因子)。这使我们能够证明,当$d \leq 3$的对数凹最大似然估计达到极大极小最优率(对数因子时,$d = 2,3$)相对于平方海灵格损失。

英文摘要:

The estimation of a log-concave density on $\mathbb{R}^d$ represents a central problem in the area of nonparametric inference under shape constraints. In this paper, we study the performance of log-concave density estimators with respect to global loss functions, and adopt a minimax approach. We first show that no statistical procedure based on a sample of size $n$ can estimate a log-concave density with respect to the squared Hellinger loss function with supremum risk smaller than order $n^{-4/5}$, when $d=1$, and order $n^{-2/(d+1)}$ when $d \geq 2$. In particular, this reveals a sense in which, when $d \geq 3$, log-concave density estimation is fundamentally more challenging than the estimation of a density with two bounded derivatives (a problem to which it has been compared). Second, we show that for $d \leq 3$, the Hellinger $ε$-bracketing entropy of a class of log-concave densities with small mean and covariance matrix close to the identity grows like $\max\{ε^{-d/2},ε^{-(d-1)}\}$ (up to a logarithmic factor when $d=2$). This enables us to prove that when $d \leq 3$ the log-concave maximum likelihood estimator achieves the minimax optimal rate (up to logarithmic factors when $d = 2,3$) with respect to squared Hellinger loss.

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。

↑