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 1911.06358cs.CC
收藏

使用半空间学习DNF的难度

Hardness of Learning DNFs using Halfspaces

Suprovat Ghoshal, Rishi Saket

摘要:

自从Valiant(STOC 1984)引入PAC模型以来,学习$t$项DNF公式(对于$t = O(1)$)的问题在PAC模型中得到了广泛的研究。仅当$t$,即,当它是一个AND时,而Khot和Saket(FOCS 2008)证明,即使使用常数项DNF弱学习$2$项DNF也是NP困难的。另一方面,Feldman等人(FOCS 2009)表明了使用半空间弱学习噪声AND的困难-后者是AND的推广,而Khot和Saket(STOC 2008)表明两个半空间的交集很难使用任何恒定的半空间函数弱学习。一个$2$ -term DNF是否可以通过使用$2$有效地学习的问题,还是经常使用许多半空间仍然是开放的。在这项工作中,我们回答了这个问题的负面显示的硬度弱学习$2$长期DNF以及嘈杂的与使用任何函数的一个常数的半空间。特别是我们证明了以下内容。对于任何常数$ν, ζ> 0$和$\ell \in \mathbb{N}$,给定点-值对$\{0,1\}^n \times \{0,1\}$上的分布,决定是否是NP困难的,YES情况:存在一个$2$项DNF,它对分布的所有点进行分类,并且存在一个AND,它对至少$1-ζ$部分点进行正确分类。无病例:任何依赖于至多$\ell$半空间的布尔函数正确地分类至多$1/2 + ν$分数的分布点。我们的结果推广和加强了以前的最佳结果上面提到的学习$2$ -term DNF的难度,学习两个半空间的交集,学习一个嘈杂的AND。

英文摘要:

The problem of learning $t$-term DNF formulas (for $t = O(1)$) has been studied extensively in the PAC model since its introduction by Valiant (STOC 1984). A $t$-term DNF can be efficiently learnt using a $t$-term DNF only if $t = 1$ i.e., when it is an AND, while even weakly learning a $2$-term DNF using a constant term DNF was shown to be NP-hard by Khot and Saket (FOCS 2008). On the other hand, Feldman et al. (FOCS 2009) showed the hardness of weakly learning a noisy AND using a halfspace -- the latter being a generalization of an AND, while Khot and Saket (STOC 2008) showed that an intersection of two halfspaces is hard to weakly learn using any function of constantly many halfspaces. The question of whether a $2$-term DNF is efficiently learnable using $2$ or constantly many halfspaces remained open. In this work we answer this question in the negative by showing the hardness of weakly learning a $2$-term DNF as well as a noisy AND using any function of a constant number of halfspaces. In particular we prove the following. For any constants $ν, ζ> 0$ and $\ell \in \mathbb{N}$, given a distribution over point-value pairs $\{0,1\}^n \times \{0,1\}$, it is NP-hard to decide whether, YES Case: There is a $2$-term DNF that classifies all the points of the distribution, and an AND that classifies at least $1-ζ$ fraction of the points correctly. NO Case: Any boolean function depending on at most $\ell$ halfspaces classifies at most $1/2 + ν$ fraction of the points of the distribution correctly. Our result generalizes and strengthens the previous best results mentioned above on the hardness of learning a $2$-term DNF, learning an intersection of two halfspaces, and learning a noisy AND.

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。

↑