几乎最优真学习与检验多项式
Almost Optimal Proper Learning and Testing Polynomials
摘要:
我们给出了均匀分布下布尔稀疏多元多项式的第一个几乎最优的多项式时间正确学习算法。对于$s$-$n$变量上的稀疏多项式和$ε=1/s^β$,$β>1$,我们的算法进行$$q_U=\left(\frac{s}ε\right)^{\frac{\log β}β+O(\frac{1}β)}+ \tilde O\left(s\right)\left(\log\frac{1}ε\right)\log n$$查询.注意,我们的查询复杂度在$1/ε$中是次线性的,在$s$中几乎是线性的。所有以前的算法的查询复杂度至少在$s$中是二次的,在$1/ε$中是线性的。然后证明了$$q_L=\left(\frac{s}ε\right)^{\frac{\log β}β+Ω(\frac{1}β)}+ Ω\left(s\right)\left(\log\frac{1}ε\right)\log n,$$的几乎紧下界。应用上述算法在~\cite{Bshouty19b}中的约化,我们给出了$s$-稀疏多项式的第一个几乎最优多项式时间检验器。我们的$β>3.404$测试人员进行$$\tilde O\left(\frac{s}ε\right)$$查询。
英文摘要:
We give the first almost optimal polynomial-time proper learning algorithm of Boolean sparse multivariate polynomial under the uniform distribution. For $s$-sparse polynomial over $n$ variables and $ε=1/s^β$, $β>1$, our algorithm makes $$q_U=\left(\frac{s}ε\right)^{\frac{\log β}β+O(\frac{1}β)}+ \tilde O\left(s\right)\left(\log\frac{1}ε\right)\log n$$ queries. Notice that our query complexity is sublinear in $1/ε$ and almost linear in $s$. All previous algorithms have query complexity at least quadratic in $s$ and linear in $1/ε$. We then prove the almost tight lower bound $$q_L=\left(\frac{s}ε\right)^{\frac{\log β}β+Ω(\frac{1}β)}+ Ω\left(s\right)\left(\log\frac{1}ε\right)\log n,$$ Applying the reduction in~\cite{Bshouty19b} with the above algorithm, we give the first almost optimal polynomial-time tester for $s$-sparse polynomial. Our tester, for $β>3.404$, makes $$\tilde O\left(\frac{s}ε\right)$$ queries.
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。