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 1710.08952stat.ML
收藏

估计包围法的操作特性

Estimating the Operating Characteristics of Ensemble Methods

Anthony Gamst, Jay-Calvin Reyes, Alden Walker

摘要:

在本文中,我们提出了一种技术,使用自助估计的操作特性和它们的变化,某些类型的集成方法。如果训练数据集很大,则自举模型可能需要大量的工作。幸运的是,在许多情况下,这项技术可以让我们确定无限恢复的影响,而无需实际改装单个模型。我们应用该技术的随机森林的元参数选择的研究。我们证明,替代引导聚合和考虑\sqrt{d}功能,分裂每个节点,其中d是功能的数量,可以产生预测精度的提高。

英文摘要:

In this paper we present a technique for using the bootstrap to estimate the operating characteristics and their variability for certain types of ensemble methods. Bootstrapping a model can require a huge amount of work if the training data set is large. Fortunately in many cases the technique lets us determine the effect of infinite resampling without actually refitting a single model. We apply the technique to the study of meta-parameter selection for random forests. We demonstrate that alternatives to bootstrap aggregation and to considering \sqrt{d} features to split each node, where d is the number of features, can produce improvements in predictive accuracy.

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。

↑