.png){kind=icon}
返回
ADAPTATION IN LOG-CONCAVE DENSITY ESTIMATION
.png){kind=icon}
OA
AI
DOI：10.1214/17-AOS1619.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The log-concave maximum likelihood estimator of a density on the real line based on a sample of size n is known to attain the minimax optimal rate of convergence of O(n(-4/5)) with respect to, for example, squared Hellinger distance. In this paper, we show that it also enjoys attractive adaptation properties, in the sense that it achieves a faster rate of convergence when the logarithm of the true density is k-affine (i.e., made up of k-affine pieces), or close to k-affine, provided in each case that k is not too large. Our results use two different techniques: the first relies on a new Marshall's inequality for log-concave density estimation, and reveals that when the true density is close to log-linear on its support, the log-concave maximum likelihood estimator can achieve the parametric rate of convergence in total variation distance. Our second approach depends on local bracketing entropy methods, and allows us to prove a sharp oracle inequality, which implies in particular a risk bound with respect to various global loss functions, including Kullback-Leibler divergence, of O(k/n log(5/4)(en/k)) when the true density is log-concave and its logarithm is close to k-affine.
Keyword:
Adaptation
bracketing entropy
log-concavity
maximum likelihood estimation
Marshall's inequality
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.7
论文数:
2.8K
被引数:
2.9W
机构
引用论文
NONPARAMETRIC LEAST SQUARES ESTIMATION OF A MULTIVARIATE CONVEX REGRESSION FUNCTION多元凸回归函数的非参数最小二乘估计.png)
ANNALS OF STATISTICSOAAI
ANNALS OF STATISTICSIF3.7
OAAI分享收藏APPROXIMATION BY LOG-CONCAVE DISTRIBUTIONS, WITH APPLICATIONS TO REGRESSIONANNALS OF STATISTICSOAAI
ANNALS OF STATISTICSIF3.7
OAAI分享收藏Logcondens: Computations Related to Univariate Log-Concave Density EstimationLogcondens: 与单变量对数凹密度估计有关的计算
OAAI
OAAI分享收藏
查看更多内容