BriefGPT.xyz
Apr, 2024
线性模型中迭代算法的不确定性量化及其在提前停止中的应用
Uncertainty quantification for iterative algorithms in linear models with application to early stopping
HTML
PDF
Pierre C. Bellec, Kai Tan
TL;DR
研究了高维线性回归问题中,使用迭代算法得到的迭代次数从1到T的变量,并提出了估计器来估计迭代过程中的泛化误差,并应用于提前停止等问题。通过仿真实验证明了理论结果。
Abstract
This paper investigates the iterates $\hbb^1,\dots,\hbb^T$ obtained from
iterative algorithms
in
high-dimensional linear regression
problems, in the regime where the feature dimension $p$ is comparable with the s
→