We study gradient testing and gradient estimation of smooth functions using only a comparison oracle that, given two points, indicates which one has the larger function value. For any smooth $f\colon\mathbb R^n\to\mathbb R$, $\mathbf{x}\in\mathbb R^n$, and $\varepsilon>0$, we design a gradient testing algorithm that determines whether the normalized gradient $\nabla f(\mathbf{x})/\|\nabla f(\mathbf{x})\|$ is $\varepsilon$-close or $2\varepsilon$-far from a given unit vector $\mathbf{v}$ using $O(1)$ queries, as well as a gradient estimation algorithm that outputs an $\varepsilon$-estimate of $\nabla f(\mathbf{x})/\|\nabla f(\mathbf{x})\|$ using $O(n\log(1/\varepsilon))$ queries which we prove to be optimal. Furthermore, we study gradient estimation in the quantum comparison oracle model where queries can be made in superpositions, and develop a quantum algorithm using $O(\log (n/\varepsilon))$ queries.
翻译:我们研究仅使用比较预言机对光滑函数进行梯度测试与梯度估计的方法,该预言机在给定两个点时,指示哪个点具有更大的函数值。对于任意光滑函数 $f\colon\mathbb R^n\to\mathbb R$、点 $\mathbf{x}\in\mathbb R^n$ 及精度 $\varepsilon>0$,我们设计了一种梯度测试算法,该算法使用 $O(1)$ 次查询即可判定归一化梯度 $\nabla f(\mathbf{x})/\|\nabla f(\mathbf{x})\|$ 与给定单位向量 $\mathbf{v}$ 的距离是 $\varepsilon$-接近还是 $2\varepsilon$-远离;同时设计了一种梯度估计算法,该算法使用 $O(n\log(1/\varepsilon))$ 次查询即可输出 $\nabla f(\mathbf{x})/\|\nabla f(\mathbf{x})\|$ 的 $\varepsilon$-估计值,我们证明该查询复杂度是最优的。此外,我们研究了量子比较预言机模型下的梯度估计问题,其中查询可以以叠加态形式进行,并开发了一种使用 $O(\log (n/\varepsilon))$ 次查询的量子算法。