arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.00637cs.DScs.CCcs.LG
收藏

在几乎多项式时间内正确学习决策树

Properly learning decision trees in almost polynomial time

Stanford(斯坦福大学);MIT(麻省理工学院)

Guy Blanc, Jane Lange, Mingda Qiao, Li-Yang Tan

摘要:

本文给出了一个在$\{\pm 1\}^n$上均匀分布下正确地、不可知地学习决策树的$n^{O(\log\log n)}$ -时间成员查询算法.即使在可实现的设置中,以前最快的运行时是$n^{O(\log n)}$,这是Escherichfeucht和Haussler的经典算法的结果。我们的算法与学习决策树的实际算法有相似之处,我们增加了额外的想法,以规避已知的下限对这些算法。为了分析我们的算法,我们证明了一个新的结构结果决策树,加强了奥唐纳,萨克斯,施拉姆,和Servedio定理。虽然OSSS定理说,每棵决策树都有一个有影响力的变量,但我们展示了如何对每棵决策树进行“修剪”,使生成的树中的每个变量都有影响力。

英文摘要:

We give an $n^{O(\log\log n)}$-time membership query algorithm for properly and agnostically learning decision trees under the uniform distribution over $\{\pm 1\}^n$. Even in the realizable setting, the previous fastest runtime was $n^{O(\log n)}$, a consequence of a classic algorithm of Ehrenfeucht and Haussler. Our algorithm shares similarities with practical heuristics for learning decision trees, which we augment with additional ideas to circumvent known lower bounds against these heuristics. To analyze our algorithm, we prove a new structural result for decision trees that strengthens a theorem of O'Donnell, Saks, Schramm, and Servedio. While the OSSS theorem says that every decision tree has an influential variable, we show how every decision tree can be "pruned" so that every variable in the resulting tree is influential.

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。

↑