arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.03994cs.DScs.AIcs.LG
收藏

保证最坏情况更新时间的全动态近似决策树

Fully-Dynamic Approximate Decision Trees With Worst-Case Update Time Guarantees

University of Milan(米兰大学);Institut Polytechnique de Paris(巴黎理工学院);Télécom Paris(巴黎电信学院)

Marco Bressan, Mauro Sozio

摘要:

我们给出了第一个算法,保持一个近似的决策树在一个任意序列的插入和删除标记的例子,在最坏情况下的运行时间每个更新请求的强有力的保证。例如,我们展示了如何维护一个决策树,其中每个顶点都有基尼增益内的最佳附加$α$通过执行$O\Big(\frac{d\,(\log n)^4}{α^3}\Big)$基本操作每次更新,其中$d$是功能的数量和$n$的最大大小的活动集(更新请求的净结果)。我们给出了类似的信息增益和方差增益的界限。事实上,所有这些界限都是一个更一般的结果的推论,用决策规则来表述--给定一组$S$标记示例的函数,决定是分割$S$还是预测一个标记。决策规则给出了贪婪决策树算法的统一视图,而不管示例和标签域,并导致$ε$ -近似决策树的一般概念,对于自然决策规则,如ID 3或C4.5所使用的规则,意味着上述增益近似保证。我们工作的核心提供了一个确定性算法,给定任何决策规则和任何$ε> 0$,使用每次更新的$O\!\left(\frac{d\, f(n)}{n} \operatorname{poly}\frac{h}ε\right)$操作维护一个$ε$近似树,其中$f(n)$是在一组$n$示例上评估规则的复杂度,$h$是维护的树的最大高度。

英文摘要:

We give the first algorithm that maintains an approximate decision tree over an arbitrary sequence of insertions and deletions of labeled examples, with strong guarantees on the worst-case running time per update request. For instance, we show how to maintain a decision tree where every vertex has Gini gain within an additive $α$ of the optimum by performing $O\Big(\frac{d\,(\log n)^4}{α^3}\Big)$ elementary operations per update, where $d$ is the number of features and $n$ the maximum size of the active set (the net result of the update requests). We give similar bounds for the information gain and the variance gain. In fact, all these bounds are corollaries of a more general result, stated in terms of decision rules -- functions that, given a set $S$ of labeled examples, decide whether to split $S$ or predict a label. Decision rules give a unified view of greedy decision tree algorithms regardless of the example and label domains, and lead to a general notion of $ε$-approximate decision trees that, for natural decision rules such as those used by ID3 or C4.5, implies the gain approximation guarantees above. The heart of our work provides a deterministic algorithm that, given any decision rule and any $ε> 0$, maintains an $ε$-approximate tree using $O\!\left(\frac{d\, f(n)}{n} \operatorname{poly}\frac{h}ε\right)$ operations per update, where $f(n)$ is the complexity of evaluating the rule over a set of $n$ examples and $h$ is the maximum height of the maintained tree.

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。

↑