arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1903.09367math.STstat.COstat.MLstat.TH
收藏

基于隐正则化的高维线性回归

High-Dimensional Linear Regression via Implicit Regularization

Peng Zhao, Yun Yang, Qiao-Chu He

摘要:

高维线性回归的许多统计估计是M-估计,通过最小化数据依赖的平方损失函数和正则化函数形成。本文考虑了一类新的估计量,它是通过一个过参数化的离散梯度动态系统隐式定义的。我们表明,在适当的限制等距条件下,overparameterization导致隐式正则化:如果我们直接应用梯度下降的残差平方和与足够小的初始值,然后在一些适当的早期停止规则,迭代收敛到一个近稀疏率最优解,提高了显式正则化的方法。特别地,所得到的估计器不遭受由于显式惩罚而导致的额外偏差,并且当信噪比足够高时可以实现参数根n速率。我们还进行了模拟,比较我们的方法与高维线性回归显式正则化。我们的研究结果说明了在稀疏向量估计中使用隐式正则化后通过梯度下降的优势。

英文摘要:

Many statistical estimators for high-dimensional linear regression are M-estimators, formed through minimizing a data-dependent square loss function plus a regularizer. This work considers a new class of estimators implicitly defined through a discretized gradient dynamic system under overparameterization. We show that under suitable restricted isometry conditions, overparameterization leads to implicit regularization: if we directly apply gradient descent to the residual sum of squares with sufficiently small initial values, then under some proper early stopping rule, the iterates converge to a nearly sparse rate-optimal solution that improves over explicitly regularized approaches. In particular, the resulting estimator does not suffer from extra bias due to explicit penalties, and can achieve the parametric root-n rate when the signal-to-noise ratio is sufficiently high. We also perform simulations to compare our methods with high dimensional linear regression with explicit regularization. Our results illustrate the advantages of using implicit regularization via gradient descent after overparameterization in sparse vector estimation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑