arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.08780cs.LGstat.ML
收藏

极快的决策树

Extremely Fast Decision Tree

Monash University(莫纳什大学)

Chaitanya Manapragada, Geoff Webb, Mahsa Salehi

摘要:

我们介绍了一种新的增量决策树学习算法,Hoeffding任意时间树,这是统计上更有效的比目前的国家的最先进的,Hoeffding树。我们证明了Hoeffding Anytime Tree的实现-“极快决策树“,对Hoeffding Tree的MOA实现的微小修改-在UCI存储库中最大的分类数据集上获得了显着优越的prequential准确性。Hoeffding Anytime Tree在极限下产生渐近批处理树,对概念漂移具有自然弹性,并且在大多数情况下可以用作Hoeffding Tree的更高精度替代品,只需少量额外的计算成本。

英文摘要:

We introduce a novel incremental decision tree learning algorithm, Hoeffding Anytime Tree, that is statistically more efficient than the current state-of-the-art, Hoeffding Tree. We demonstrate that an implementation of Hoeffding Anytime Tree---"Extremely Fast Decision Tree", a minor modification to the MOA implementation of Hoeffding Tree---obtains significantly superior prequential accuracy on most of the largest classification datasets from the UCI repository. Hoeffding Anytime Tree produces the asymptotic batch tree in the limit, is naturally resilient to concept drift, and can be used as a higher accuracy replacement for Hoeffding Tree in most scenarios, at a small additional computational cost.

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。

↑