arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0909.5011cs.CCcs.DM
收藏

多项式阈值函数的平均灵敏度和噪声灵敏度

Average sensitivity and noise sensitivity of polynomial threshold functions

Ilias Diakonikolas, Prasad Raghavendra, Rocco A. Servedio, Li-Yang Tan

摘要:

给出了次数为$d$的多项式阈值函数(PTFs)的平均灵敏度和噪声灵敏度的第一个非平凡上界。这些界限对于布尔超立方体上的PTF和标准$n$维高斯分布下的$\R^n$上的PTF都成立。我们的边界上的布尔平均灵敏度的PTF表示的进展,对解决的猜想Gotsman和Linial \cite{GL:94},这说明对称函数切片的中间层的布尔超立方体的$d$具有最高的平均灵敏度的所有度- $d$ PTF。通过Kalai等人的$L_1$多项式回归算法\cite{KKMS:08},我们对高斯和布尔噪声灵敏度的界限为这些输入分布下的大类常度PTF产生多项式时间不可知的学习算法。用于获得我们的平均和噪声灵敏度的PTFs在高斯设置的边界的主要成分是尾部边界和反浓度边界的高斯随机变量\cite{Janson:97,CW:01}的低次多项式。为了得到我们的布尔平均灵敏度的PTFs的界限,我们推广的“临界指数”机制的\cite{Servedio:07cc}(在这项工作中适用于半空间,即度1 PTFs)一般PTFs。与\cite{MOO:05}的“不变性原则”一起,这使我们能够将我们的技术从高斯设置扩展到布尔设置。我们的布尔噪声灵敏度的界限是通过一个简单的减少从上界的平均灵敏度的布尔PTFs的噪声灵敏度相应的界限。

英文摘要:

We give the first non-trivial upper bounds on the average sensitivity and noise sensitivity of degree-$d$ polynomial threshold functions (PTFs). These bounds hold both for PTFs over the Boolean hypercube and for PTFs over $\R^n$ under the standard $n$-dimensional Gaussian distribution. Our bound on the Boolean average sensitivity of PTFs represents progress towards the resolution of a conjecture of Gotsman and Linial \cite{GL:94}, which states that the symmetric function slicing the middle $d$ layers of the Boolean hypercube has the highest average sensitivity of all degree-$d$ PTFs. Via the $L_1$ polynomial regression algorithm of Kalai et al. \cite{KKMS:08}, our bounds on Gaussian and Boolean noise sensitivity yield polynomial-time agnostic learning algorithms for the broad class of constant-degree PTFs under these input distributions. The main ingredients used to obtain our bounds on both average and noise sensitivity of PTFs in the Gaussian setting are tail bounds and anti-concentration bounds on low-degree polynomials in Gaussian random variables \cite{Janson:97,CW:01}. To obtain our bound on the Boolean average sensitivity of PTFs, we generalize the ``critical-index'' machinery of \cite{Servedio:07cc} (which in that work applies to halfspaces, i.e. degree-1 PTFs) to general PTFs. Together with the "invariance principle" of \cite{MOO:05}, this lets us extend our techniques from the Gaussian setting to the Boolean setting. Our bound on Boolean noise sensitivity is achieved via a simple reduction from upper bounds on average sensitivity of Boolean PTFs to corresponding bounds on noise sensitivity.

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。

↑