The Lasso is a method for high-dimensional regression, which is now commonly used when the number of covariates $p$ is of the same order or larger than the number of observations $n$. Classical asymptotic normality theory does not apply to this model due to two fundamental reasons: $(1)$ The regularized risk is non-smooth; $(2)$ The distance between the estimator $\widehat{\boldsymbol{\theta}}$ and the true parameters vector $\boldsymbol{\theta}^*$ cannot be neglected. As a consequence, standard perturbative arguments that are the traditional basis for asymptotic normality fail. On the other hand, the Lasso estimator can be precisely characterized in the regime in which both $n$ and $p$ are large and $n/p$ is of order one. This characterization was first obtained in the case of Gaussian designs with i.i.d. covariates: here we generalize it to Gaussian correlated designs with non-singular covariance structure. This is expressed in terms of a simpler ``fixed-design'' model. We establish non-asymptotic bounds on the distance between the distribution of various quantities in the two models, which hold uniformly over signals $\boldsymbol{\theta}^*$ in a suitable sparsity class and over values of the regularization parameter. As an application, we study the distribution of the debiased Lasso and show that a degrees-of-freedom correction is necessary for computing valid confidence intervals.
翻译:Lasso 是高维回归的一种方法, 当共差值的美元值与观测值的顺序相同或更高时, 通常使用这一方法。 经典无症状常态理论不适用于这个模型, 原因有两个: $(1)美元 正常化的风险是非单向的; $(2)美元, 估计器 $\ bloyhat_ boldsymbol_theta $ 美元 和真正的参数矢量 $\boldsysylsol_theta ⁇ $ 不能忽略。 因此, 标准性扰动参数是常态常态常态常态常态常态的基数 。 另一方面, Lasso 估计器可以精确地描述于一个制度, 美元和美元都是大的, 美元/ 美元是顺序的。 这种定性首先在高斯的设计中以 I. d. d. comblatesality 格式, 我们用非正态性常态的常态常态的常态 度 度 度, 显示我们在两个稳性 格式 的 格式 的 的 的 格式 的 的 的 的 格式 的 的 格式 的 的 格式 中, 显示一个简单的 。