快速决策树学习解决困难的编码理论问题
Fast decision tree learning solves hard coding-theoretic problems
AI总结:
本文将正确PAC学习决策树问题与参数化最近码字问题($k$-NCP)联系起来,证明改进现有拟多项式时间决策树学习算法即可为$k$-NCP带来指数级改进的近似算法,并基于不可近似性结果排除了多项式时间算法。
摘要:
我们将正确 PAC 学习决策树的问题与参数化最近码字问题($k$-NCP)联系起来。尽管相关社区付出了巨大努力,但这两个问题的算法进展均停滞不前:前者的已知最快算法运行在拟多项式时间内(Ehrenfeucht 和 Haussler 1989),后者的已知最佳近似比为 $O(n/\log n)$(Berman 和 Karpinsky 2002;Alon, Panigrahy, 和 Yekhanin 2009)。迄今为止,对这两个问题的研究均独立进行,未发现已知联系。我们证明,对 Ehrenfeucht 和 Haussler 算法的任何改进,都将为 $k$-NCP 产生 $O(\log n)$-近似算法,这是对当前技术水平的指数级改进。这既可以被解释为设计 $k$-NCP 算法的新途径,也可以被解释为确立 Ehrenfeucht 和 Haussler 算法最优性的新途径。此外,我们的归约结合 $k$-NCP 现有的不可近似性结果,已经排除了正确学习决策树的多项式时间算法。我们硬度结果的一个显著特点是,它们甚至在弱学习设定下也成立,而先前的结果仅限于强学习设定。
英文摘要:
We connect the problem of properly PAC learning decision trees to the parameterized Nearest Codeword Problem ($k$-NCP). Despite significant effort by the respective communities, algorithmic progress on both problems has been stuck: the fastest known algorithm for the former runs in quasipolynomial time (Ehrenfeucht and Haussler 1989) and the best known approximation ratio for the latter is $O(n/\log n)$ (Berman and Karpinsky 2002; Alon, Panigrahy, and Yekhanin 2009). Research on both problems has thus far proceeded independently with no known connections. We show that $\textit{any}$ improvement of Ehrenfeucht and Haussler's algorithm will yield $O(\log n)$-approximation algorithms for $k$-NCP, an exponential improvement of the current state of the art. This can be interpreted either as a new avenue for designing algorithms for $k$-NCP, or as one for establishing the optimality of Ehrenfeucht and Haussler's algorithm. Furthermore, our reduction along with existing inapproximability results for $k$-NCP already rule out polynomial-time algorithms for properly learning decision trees. A notable aspect of our hardness results is that they hold even in the setting of $\textit{weak}$ learning whereas prior ones were limited to the setting of strong learning.
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。