We consider both $\ell _{0}$-penalized and $\ell _{0}$-constrained quantile regression estimators. For the $\ell _{0}$-penalized estimator, we derive an exponential inequality on the tail probability of excess quantile prediction risk and apply it to obtain non-asymptotic upper bounds on the mean-square parameter and regression function estimation errors. We also derive analogous results for the $\ell _{0}$-constrained estimator. The resulting rates of convergence are nearly minimax-optimal and the same as those for $\ell _{1}$-penalized and non-convex penalized estimators. Further, we characterize expected Hamming loss for the $\ell _{0}$-penalized estimator. We implement the proposed procedure via mixed integer linear programming and also a more scalable first-order approximation algorithm. We illustrate the finite-sample performance of our approach in Monte Carlo experiments and its usefulness in a real data application concerning conformal prediction of infant birth weights (with $n\approx 10^{3}$ and up to $p>10^{3}$). In sum, our $\ell _{0}$-based method produces a much sparser estimator than the $\ell _{1}$-penalized and non-convex penalized approaches without compromising precision.
翻译:本文考虑了$\ell_{0}$惩罚和$\ell_{0}$限制的分位数回归估计器。对于$\ell_{0}$惩罚的估计器,我们推导了超过分位数预测风险的尾部概率的指数不等式,并应用它来得到关于均方参数和回归函数估计误差的非渐近上界。我们还为$\ell_{0}$受限估计器导出类似的结果。得到的收敛速率几乎是最小极小值的,与$\ell_{1}$惩罚和非凸惩罚估计器的速率相同。此外,我们还表征了$\ell_{0}$惩罚估计器的期望Hamming损失。我们通过混合整数线性规划实现了所提出的过程,以及更可扩展的一阶近似算法。我们在Monte Carlo实验中展示了我们方法的有限样本性能,并说明了它在有关婴儿出生体重的真实数据应用中($n \approx 10^{3}$,$p>10^{3}$)的有用性。总之,我们的$\ell_{0}$方法产生了比$\ell_{1}$惩罚和非凸惩罚方法更稀疏的估计,而不会影响精度。