Parallel Bayesian Additive Regression Trees
Parallel Bayesian Additive Regression Trees
复制标题
并行贝叶斯加性回归树
DOI：
10.1080/10618600.2013.841584
复制
发表时间：
2013
影响因子：
2.4
通讯作者：
W. Rust
中科院分区：
文献类型：
--
作者：
M. Pratola;H. Chipman;J. Gattiker;D. Higdon;R. McCulloch;W. Rust
贝叶斯加性回归树（Bayesian additive regression trees，BART）是一种灵活的非线性回归的贝叶斯方法，已被证明与最好的现代预测方法（如基于bagging和boosting的方法）竞争。BART提供了一些优势。例如，随机搜索马尔可夫链蒙特卡罗（MCMC）算法可以提供对模型空间的更完整的搜索，并且MCMC绘制之间的变化可以以通常的贝叶斯方式捕获不确定性水平。BART先验是稳健的，因为通常使用默认先验规范获得合理的结果。然而，在R软件包BayesTree中公开的BART算法的实现速度不够快，不能被认为是与超过一千个观察结果交互的，甚至不太可能运行50，000到100，000个观察结果。在这篇文章中，我们将展示如何修改BART算法，然后使用消息传递接口（MPI）库实现的单程序多数据（SPMD）并行计算进行计算。该方法在处理器内核数量上几乎线性扩展，使从业者能够对大量数据集进行统计推断。我们的方法还可以处理太大而无法容纳在任何单个数据存储库中的数据集。
Bayesian additive regression trees (BART) is a Bayesian approach to flexible nonlinear regression which has been shown to be competitive with the best modern predictive methods such as those based on bagging and boosting. BART offers some advantages. For example, the stochastic search Markov chain Monte Carlo (MCMC) algorithm can provide a more complete search of the model space and variation across MCMC draws can capture the level of uncertainty in the usual Bayesian way. The BART prior is robust in that reasonable results are typically obtained with a default prior specification. However, the publicly available implementation of the BART algorithm in the R package BayesTree is not fast enough to be considered interactive with over a thousand observations, and is unlikely to even run with 50,000 to 100,000 observations. In this article we show how the BART algorithm may be modified and then computed using single program, multiple data (SPMD) parallel computation implemented using the Message Passing Interface (MPI) library. The approach scales nearly linearly in the number of processor cores, enabling the practitioner to perform statistical inference on massive datasets. Our approach can also handle datasets too massive to fit on any single data repository.