Rates of convergence for random forests via generalized U-statistics
Rates of convergence for random forests via generalized U-statistics
复制标题
通过广义 U 统计得出随机森林的收敛率
DOI：
--
复制
发表时间：
2019
影响因子：
1.1
通讯作者：
L. Mentch
中科院分区：
文献类型：
--
作者：
Weiguang Peng;T. Coleman;L. Mentch
随机森林仍然是最流行的现成监督学习算法之一。然而，尽管他们在经验上取得了成功，但直到最近，几乎没有理论结果可以描述他们的表现和行为。在这项工作中，我们通过建立随机森林和其他监督学习集成的收敛率，超越了最近关于一致性和渐近正态性的工作。我们发展了广义u统计量的概念，并表明在这个框架内，随机森林预测可能在比以前建立的更大的子样本量下保持渐近正态。我们还提供了Berry-Esseen界，以量化这种收敛发生的速度，明确了子样本大小和树的数量在确定随机森林预测分布中的作用。
Random forests remain among the most popular off-the-shelf supervised learning algorithms. Despite their well-documented empirical success, however, until recently, few theoretical results were available to describe their performance and behavior. In this work we push beyond recent work on consistency and asymptotic normality by establishing rates of convergence for random forests and other supervised learning ensembles. We develop the notion of generalized U-statistics and show that within this framework, random forest predictions can potentially remain asymptotically normal for larger subsample sizes than previously established. We also provide Berry-Esseen bounds in order to quantify the rate at which this convergence occurs, making explicit the roles of the subsample size and the number of trees in determining the distribution of random forest predictions.
DOI：
--
发表时间：
2019-11
期刊：
J. Mach. Learn. Res.
影响因子：
--
作者：
L. Mentch;Siyu Zhou
通讯作者：
L. Mentch;Siyu Zhou
近似高维无限阶 $U$-统计：统计和计算保证
影响因子：
1.1
作者：
Song, Yanglei;Chen, Xiaohui;Kato, Kengo
通讯作者：
Kato, Kengo