We prove various theorems on approximation using polynomials with integer coefficients in the Bernstein basis of any given order. In the extreme, we draw the coefficients from $\{ \pm 1\}$ only. A basic case of our results states that for any Lipschitz function $f:[0,1] \to [-1,1]$ and for any positive integer $n$, there are signs $\sigma_0,\dots,\sigma_n \in \{\pm 1\}$ such that $$\left |f(x) - \sum_{k=0}^n \sigma_k \, \binom{n}{k} x^k (1-x)^{n-k} \right | \leq \frac{C (1+|f|_{\mathrm{Lip}})}{1+\sqrt{nx(1-x)}} ~\mbox{ for all } x \in [0,1].$$ More generally, we show that higher accuracy is achievable for smoother functions: For any integer $s\geq 1$, if $f$ has a Lipschitz $(s{-}1)$st derivative, then approximation accuracy of order $O(n^{-s/2})$ is achievable with coefficients in $\{\pm 1\}$ provided $\|f \|_\infty < 1$, and of order $O(n^{-s})$ with unrestricted integer coefficients, both uniformly on closed subintervals of $(0,1)$ as above. Hence these polynomial approximations are not constrained by the saturation of classical Bernstein polynomials. Our approximations are constructive and can be implemented using feedforward neural networks whose weights are chosen from $\{\pm 1\}$ only.
翻译:在任何给定顺序的 Bernstein 基调中,我们用具有整数系数的多元数值来证明近似上的不同理论。 在极端的方面, 我们只能从$\\ pm 1\\ 美元中提取系数。 我们结果的一个基本案例表明, 对于任何利普西茨函数 $f: [0, 1\ to [1, 1, 1美元] 和任何正整数美元来说, 有 $gma_ 0,\ dots,\ sgma_n\ n% pm 1 美元, 等於 left (x) -\ sum_ k=0\ n\ ssgma_k\,\ binom{ k} x k k (1-x) (1)\\\ leqn\ frm{c{c} 任何正整数( 1\\\ fxx) 。 [% kblational_xxxxx 美元, 我们的精确度是 slock____ 美元 。