有界独立傻瓜半空间
Bounded Independence Fools Halfspaces
摘要:
我们证明了{-1,1}^n上的任意k方向独立分布欺骗了任意半空间h,且误差为\eps,k = O(\log^2(1/ \eps)/ \eps^2).直到对数因子,我们的结果与Benjamini,Gurel-Gurevich和Peled(2007)的下限相匹配,表明k = Ω(1/(\eps^2 \cdot \log(1/ \eps)。利用k-独立分布的标准构造,我们得到了愚弄半空间的第一个显式伪随机生成元G:{-1,1}^s --> {-1,1}^n。具体来说,我们用错误eps和种子长度s = k欺骗半空间\log n = O(\log n \cdot \log^2(1/ \eps)/ \eps^2)。我们的方法结合了经典的工具,从真正的近似理论与结构的结果半空间Servedio(计算复杂性2007年)。
英文摘要:
We show that any distribution on {-1,1}^n that is k-wise independent fools any halfspace h with error \eps for k = O(\log^2(1/\eps) /\eps^2). Up to logarithmic factors, our result matches a lower bound by Benjamini, Gurel-Gurevich, and Peled (2007) showing that k = Ω(1/(\eps^2 \cdot \log(1/\eps))). Using standard constructions of k-wise independent distributions, we obtain the first explicit pseudorandom generators G: {-1,1}^s --> {-1,1}^n that fool halfspaces. Specifically, we fool halfspaces with error eps and seed length s = k \log n = O(\log n \cdot \log^2(1/\eps) /\eps^2). Our approach combines classical tools from real approximation theory with structural results on halfspaces by Servedio (Computational Complexity 2007).
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。