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 $\epsilon=1/s^\beta$, $\beta>1$, our algorithm makes $$q_U=\left(\frac{s}{\epsilon}\right)^{\frac{\log \beta}{\beta}+O(\frac{1}{\beta})}+ \tilde O\left(s\right)\left(\log\frac{1}{\epsilon}\right)\log n$$ queries. Notice that our query complexity is sublinear in $1/\epsilon$ and almost linear in $s$. All previous algorithms have query complexity at least quadratic in $s$ and linear in $1/\epsilon$. We then prove the almost tight lower bound $$q_L=\left(\frac{s}{\epsilon}\right)^{\frac{\log \beta}{\beta}+\Omega(\frac{1}{\beta})}+ \Omega\left(s\right)\left(\log\frac{1}{\epsilon}\right)\log n,$$ 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 $\beta>3.404$, makes $$\tilde O\left(\frac{s}{\epsilon}\right)$$ queries.
翻译:我们给出了在统一分布下布利安稀疏多变多异性多元性的第一个近乎最佳的多元-时间学习算法。 对于美元变量和美元=1/s ⁇ beta$的粗微多元性多元性, $\beta>$, 我们的算法将美元和美元( 折合) 折合( 折合) {( frac{ 1\\\\\ beta} {\ tilde Oleft( left)\ left( right) (log\\ frafc{ 1\\\ epslon_right)\ log n$美元查询。 注意我们的查询复杂度在1\\\\\ beta>lon$和美元几乎线性。 所有前的算法在美元和1\\\\\\ eclon$( lientral) 和 美元( lientral_q__lon$( lex) lex( lex) lex( lea) lex( lex) lex( lea) lex( lea) lex( leg) leg) $( lex) $( leg) leg) leg) leg) leg) $( leg) $( lex_____________( ral\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\