A generic out-of-sample error estimate is proposed for robust $M$-estimators regularized with a convex penalty in high-dimensional linear regression where $(X,y)$ is observed and $p,n$ are of the same order. If $\psi$ is the derivative of the robust data-fitting loss $\rho$, the estimate depends on the observed data only through the quantities $\hat\psi = \psi(y-X\hat\beta)$, $X^\top \hat\psi$ and the derivatives $(\partial/\partial y) \hat\psi$ and $(\partial/\partial y) X\hat\beta$ for fixed $X$. The out-of-sample error estimate enjoys a relative error of order $n^{-1/2}$ in a linear model with Gaussian covariates and independent noise, either non-asymptotically when $p/n\le \gamma$ or asymptotically in the high-dimensional asymptotic regime $p/n\to\gamma'\in(0,\infty)$. General differentiable loss functions $\rho$ are allowed provided that $\psi=\rho'$ is 1-Lipschitz. The validity of the out-of-sample error estimate holds either under a strong convexity assumption, or for the $\ell_1$-penalized Huber M-estimator if the number of corrupted observations and sparsity of the true $\beta$ are bounded from above by $s_*n$ for some small enough constant $s_*\in(0,1)$ independent of $n,p$. For the square loss and in the absence of corruption in the response, the results additionally yield $n^{-1/2}$-consistent estimates of the noise variance and of the generalization error. This generalizes, to arbitrary convex penalty, estimates that were previously known for the Lasso.
翻译:基于凸惩罚的鲁棒M估计值的样外误差估计
翻译后的摘要:
提出了一种通用的基于样本外数据的误差估计方法,适用于高维线性回归中,采用凸惩罚的鲁棒M估计值。假设$(X,y)$是可观测的,$p$和$n$是同阶的。如果$\psi$是鲁棒数据拟合损失$\rho$的导数,则估计量仅通过量$\hat\psi = \psi(y−X\hat\beta)$、$X^\top\hat\psi$和$\hat\psi$及$X\hat\beta$对$y$的偏导数来依赖于观测数据。对于高斯协变量和独立噪声的线性模型,只要是$p/n\le \gamma$,则在非渐进性时期估计量的相对误差为$n^{-1/2}$;在$p/n\to\gamma'\in(0,\infty)$的高维渐进区域则渐进成立。若对真实$\beta$的稀疏性和有限数量的污染观测进行了严格的限制,则基于值$\hat\psi$的样外误差估计的有效性得到了保证。$\rho$ 是可导的损失函数,要满足$\psi=\rho'$的1-Lipschitz条件。本文推广了Lasso的估计结果,适用于任意凸惩罚的估计,特别是对于平方损失且响应无污染的情况,结果还提供了噪声方差和泛化误差的$n^{−1/2}$ -一致估计。