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 2205.07756cs.CC
收藏

维数对计算决策树复杂性的影响

The Influence of Dimensions on the Complexity of Computing Decision Trees

Stephen G. Kobourov, Maarten Löffler, Fabrizio Montecchiani, Marcin Pilipczuk, Ignaz Rutter, Raimund Seidel, Manuel Sorge, Jules Wulms

摘要:

决策树递归地分割特征空间$\mathbb{R}^{d}$,然后基于得到的划分分配类标签。几十年来,决策树一直是基本机器学习工具包的一部分。大量的工作将启发式算法从训练数据中计算决策树,通常旨在最小化结果树的大小。相比之下,很少有人知道的基本计算问题的复杂性计算最小尺寸的树给定的训练数据。我们研究这个问题的特征空间的维度数$d$。我们表明,它可以解决在$O(n^{2d + 1}d)$时间,但在合理的复杂性理论假设下,它是不可能实现$f(d) \cdot n^{o(d / \log d)}$运行时间,其中$n$是训练样本的数量。这个问题在$(dR)^{O(dR)} \cdot n^{1+o(1)}$时间内是可解的,如果恰好有两个类,并且$R$是用第一类标记的树叶数目的上界。

英文摘要:

A decision tree recursively splits a feature space $\mathbb{R}^{d}$ and then assigns class labels based on the resulting partition. Decision trees have been part of the basic machine-learning toolkit for decades. A large body of work treats heuristic algorithms to compute a decision tree from training data, usually aiming to minimize in particular the size of the resulting tree. In contrast, little is known about the complexity of the underlying computational problem of computing a minimum-size tree for the given training data. We study this problem with respect to the number $d$ of dimensions of the feature space. We show that it can be solved in $O(n^{2d + 1}d)$ time, but under reasonable complexity-theoretic assumptions it is not possible to achieve $f(d) \cdot n^{o(d / \log d)}$ running time, where $n$ is the number of training examples. The problem is solvable in $(dR)^{O(dR)} \cdot n^{1+o(1)}$ time, if there are exactly two classes and $R$ is an upper bound on the number of tree leaves labeled with the first~class.

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。

↑