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 1806.10057cs.CCcs.DS
收藏

你的函数是低维的吗?

Is your function low-dimensional?

Anindya De, Elchanan Mossel, Joe Neeman

摘要:

我们研究的问题,如果一个函数依赖于其输入数据的线性方向的一个小数目的测试。如果一个函数$f$完全由输入空间的某个$k$维子空间确定,则称它为线性$k$ -junta.在本文中,我们研究的问题,测试是否一个给定的$n$变量函数$f : \mathbb{R}^n \to \{0,1\}$,是一个线性$k$ -junta或$ε$ -远离所有的线性$k$ -junta,其中的接近度是相对于$\mathbb{R}^n$上的高斯测度。线性$k$ -juntas是从布尔函数分析的两个基本类的共同推广(这两个类都已经在属性测试中进行了研究)$\textbf{1.}$ $k$ - juntas是布尔立方体上的函数,它依赖于至多k个变量和$k$半空间的$\textbf{2.}$交集,一个基本的几何概念类。我们发现,类的线性$k$ -juntas是不可测的,但增加了一个表面积的限制,使其可测:我们给了一个$\mathsf{poly}(k \cdot s/ε)$查询非自适应测试仪的线性$k$ -juntas表面积最多$s$。我们表明,$s$多项式依赖是必要的。此外,我们表明,如果该函数是一个线性$k$ -junta的表面积最多$s$,我们给出了一个$(s \cdot k)^{O(k)}$ -查询非自适应算法来学习函数的旋转的基础。特别是,这意味着我们可以测试类的交叉点的$k$半空间在$\mathbb{R}^n$与查询复杂性独立的$n$。

英文摘要:

We study the problem of testing if a function depends on a small number of linear directions of its input data. We call a function $f$ a linear $k$-junta if it is completely determined by some $k$-dimensional subspace of the input space. In this paper, we study the problem of testing whether a given $n$ variable function $f : \mathbb{R}^n \to \{0,1\}$, is a linear $k$-junta or $ε$-far from all linear $k$-juntas, where the closeness is measured with respect to the Gaussian measure on $\mathbb{R}^n$. Linear $k$-juntas are a common generalization of two fundamental classes from Boolean function analysis (both of which have been studied in property testing) $\textbf{1.}$ $k$- juntas which are functions on the Boolean cube which depend on at most k of the variables and $\textbf{2.}$ intersection of $k$ halfspaces, a fundamental geometric concept class. We show that the class of linear $k$-juntas is not testable, but adding a surface area constraint makes it testable: we give a $\mathsf{poly}(k \cdot s/ε)$-query non-adaptive tester for linear $k$-juntas with surface area at most $s$. We show that the polynomial dependence on $s$ is necessary. Moreover, we show that if the function is a linear $k$-junta with surface area at most $s$, we give a $(s \cdot k)^{O(k)}$-query non-adaptive algorithm to learn the function up to a rotation of the basis. In particular, this implies that we can test the class of intersections of $k$ halfspaces in $\mathbb{R}^n$ with query complexity independent of $n$.

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。

↑