arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1806.06290cs.CC
收藏

小阈值电路的平均情况下界与可满足性算法

Average-Case Lower Bounds and Satisfiability Algorithms for Small Threshold Circuits

Ruiwen Chen, Rahul Santhanam, Srikanth Srinivasan

摘要:

$ \newcommand{\cclass}[1]{\normalfont\textsf{##1}} $我们显示平均情况下的显式布尔函数对有界深度阈值电路的超线性导线数的下限。我们表明,对于每一个整数$d > 1$,有一个常数$\varepsilon_d > 0$,使$n$位上的奇偶函数具有相关性最多$n^{-\varepsilon_d}$与深度- $d$阈值电路有最多$n^{1+\varepsilon_d}$线,和$n$位上的广义Andreev函数具有相关性最多$\exp(-{n^{\varepsilon_d}})$与深度- $d$阈值电路有最多$n^{1+\varepsilon_d}$线。以前,在这种情况下,只有最差情况下的下限是已知的(Impagliazzo,Paturi和Saks(SICOMP 1997))。我们用我们的想法在几个相关问题上取得了进展。针对具有超线性导线数的深度$d$阈值电路,给出了击败暴力搜索的可满足性算法.这是第一个深度大于2的算法。我们还表明,$n$位的奇偶校验不能计算多项式大小的$\textsf{AC}^0$电路与$n^{o(1)}$一般阈值门。以前,此设置中的奇偶校验下限不能处理多个$\log(n)$门。这个结果也暗示了在均匀分布下具有$n^{o(1)}$阈值门的$\textsf{AC}^0$的次指数时间学习算法。此外,我们给出了几乎最优的边界的深度$d$阈值电路计算平均奇偶校验门的数量,并显示平均情况下的下限阈值公式的任何深度。我们的技术包括自适应随机限制,反浓度和线性阈值函数的结构理论,以及有界读取的Buckoff界。

英文摘要:

$ \newcommand{\cclass}[1]{\normalfont\textsf{##1}} $We show average-case lower bounds for explicit Boolean functions against bounded-depth threshold circuits with a superlinear number of wires. We show that for each integer $d > 1$, there is a constant $\varepsilon_d > 0$ such that the Parity function on $n$ bits has correlation at most $n^{-\varepsilon_d}$ with depth-$d$ threshold circuits which have at most $n^{1+\varepsilon_d}$ wires, and the Generalized Andreev function on $n$ bits has correlation at most $\exp(-{n^{\varepsilon_d}})$ with depth-$d$ threshold circuits which have at most $n^{1+\varepsilon_d}$ wires. Previously, only worst-case lower bounds in this setting were known (Impagliazzo, Paturi, and Saks (SICOMP 1997)). We use our ideas to make progress on several related questions. We give satisfiability algorithms beating brute force search for depth-$d$ threshold circuits with a superlinear number of wires. These are the first such algorithms for depth greater than 2. We also show that Parity on $n$ bits cannot be computed by polynomial-size $\textsf{AC}^0$ circuits with $n^{o(1)}$ general threshold gates. Previously no lower bound for Parity in this setting could handle more than $\log(n)$ gates. This result also implies subexponential-time learning algorithms for $\textsf{AC}^0$ with $n^{o(1)}$ threshold gates under the uniform distribution. In addition, we give almost optimal bounds for the number of gates in a depth-$d$ threshold circuit computing Parity on average, and show average-case lower bounds for threshold formulas of any depth. Our techniques include adaptive random restrictions, anti-concentration and the structural theory of linear threshold functions, and bounded-read Chernoff bounds.

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。

↑