Bayesian additive regression trees (BART) are popular Bayesian ensemble models used in regression and classification analysis. Under this modeling framework, the regression function is approximated by an ensemble of decision trees, interpreted as weak learners that capture different features of the data. In this work, we propose a generalization of the BART model that has two main features: first, it automatically selects the number of decision trees using the given data; second, the model allows clusters of observations to have different regression functions since each data point can only use a selection of weak learners, instead of all of them. This model generalization is accomplished by including a binary weight matrix in the conditional distribution of the response variable, which activates only a specific subset of decision trees for each observation. Such a matrix is endowed with an Indian Buffet process prior, and sampled within the MCMC sampler, together with the other BART parameters. We then compare the Infinite BART model with the classic one on simulated and real datasets. Specifically, we provide examples illustrating variable importance, partial dependence and causal estimation.
翻译:贝叶斯加性回归树(BART)是回归与分类分析中常用的贝叶斯集成模型。在此建模框架下,回归函数通过决策树集成来近似,这些决策树被解释为能够捕捉数据不同特征的弱学习器。本研究提出了一种BART模型的泛化形式,其主要特点包括:首先,该模型能够基于给定数据自动选择决策树的数量;其次,由于每个数据点仅能使用部分弱学习器而非全部,模型允许观测簇具有不同的回归函数。这一模型泛化通过在响应变量的条件分布中引入二元权重矩阵来实现,该矩阵仅针对每个观测激活特定的决策树子集。该矩阵被赋予印度自助餐过程先验,并与其他BART参数一同在MCMC采样器中进行采样。随后,我们在模拟和真实数据集上将无限BART模型与经典模型进行比较,具体通过变量重要性、偏依赖及因果估计的示例加以说明。