We quantify the minimax rate for a nonparametric regression model over a convex function class $\mathcal{F}$ with bounded diameter. We obtain a minimax rate of ${\varepsilon^{\ast}}^2\wedge\mathrm{diam}(\mathcal{F})^2$ where \[\varepsilon^{\ast} =\sup\{\varepsilon>0:n\varepsilon^2 \le \log M_{\mathcal{F}}^{\operatorname{loc}}(\varepsilon,c)\},\] where $M_{\mathcal{F}}^{\operatorname{loc}}(\cdot, c)$ is the local metric entropy of $\mathcal{F}$ and our loss function is the squared population $L_2$ distance over our input space $\mathcal{X}$. In contrast to classical works on the topic [cf. Yang and Barron, 1999], our results do not require functions in $\mathcal{F}$ to be uniformly bounded in sup-norm. In addition, we prove that our estimator is adaptive to the true point, and to the best of our knowledge this is the first such estimator in this general setting. This work builds on the Gaussian sequence framework of Neykov [2022] using a similar algorithmic scheme to achieve the minimax rate. Our algorithmic rate also applies with sub-Gaussian noise. We illustrate the utility of this theory with examples including multivariate monotone functions, linear functionals over ellipsoids, and Lipschitz classes.

翻译：我们量化了定义在具有有界直径的凸函数类$\mathcal{F}$上的非参数回归模型的极小极大速率。我们得到了极小极大速率${\varepsilon^{\ast}}^2\wedge\mathrm{diam}(\mathcal{F})^2$，其中 \[\varepsilon^{\ast} =\sup\{\varepsilon>0:n\varepsilon^2 \le \log M_{\mathcal{F}}^{\operatorname{loc}}(\varepsilon,c)\},\] 这里$M_{\mathcal{F}}^{\operatorname{loc}}(\cdot, c)$是$\mathcal{F}$的局部度量熵，而我们的损失函数是输入空间$\mathcal{X}$上的平方总体$L_2$距离。与该主题的经典研究（参见Yang和Barron, 1999）不同，我们的结果不要求$\mathcal{F}$中的函数在无穷范数下一致有界。此外，我们证明所提出的估计量自适应于真实数据点，据我们所知，这是此通用设定下首个具有该性质的估计量。本工作基于Neykov[2022]的高斯序列框架，采用类似的算法方案以实现极小极大速率。我们的算法速率同样适用于次高斯噪声。我们通过多元单调函数、椭球线性泛函以及Lipschitz类等示例阐明了该理论的实用性。