arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1701.02110stat.MEstat.ML
收藏

转型森林

Transformation Forests

Torsten Hothorn, Achim Zeileis

摘要:

具有连续目标的监督学习问题的回归模型通常被理解为给定预测器的目标的条件均值的模型。这个概念很简单,因此吸引了解释和可视化。然而,从这些模型中无法获得关于整个潜在条件分布的信息。对回归模型作为条件分布的模型的更一般的理解允许从这样的模型进行更广泛的推断,例如预测区间的计算。几种随机森林类型算法旨在估计条件分布,最突出的是分位数回归森林(Meinshausen,2006年,JMLR)。我们提出了一种新的方法的基础上,其特征在于其转换功能的分布的参数家庭。一个专用的新的“转换树”算法能够检测分布的变化。基于这些转换树,我们引入“转换森林”作为条件分布函数的自适应局部似然估计。由此产生的模型是完全参数化的,但非常一般,并允许广泛的推理程序,如基于模型的引导,以一种简单的方式应用。

英文摘要:

Regression models for supervised learning problems with a continuous target are commonly understood as models for the conditional mean of the target given predictors. This notion is simple and therefore appealing for interpretation and visualisation. Information about the whole underlying conditional distribution is, however, not available from these models. A more general understanding of regression models as models for conditional distributions allows much broader inference from such models, for example the computation of prediction intervals. Several random forest-type algorithms aim at estimating conditional distributions, most prominently quantile regression forests (Meinshausen, 2006, JMLR). We propose a novel approach based on a parametric family of distributions characterised by their transformation function. A dedicated novel "transformation tree" algorithm able to detect distributional changes is developed. Based on these transformation trees, we introduce "transformation forests" as an adaptive local likelihood estimator of conditional distribution functions. The resulting models are fully parametric yet very general and allow broad inference procedures, such as the model-based bootstrap, to be applied in a straightforward way.

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。

↑