Can Machines Learn Weak Signals?
收藏NBER2025-02-01 更新2025-02-08 收录
下载链接：
https://www.nber.org/papers/w33421
下载链接
链接失效反馈官方服务：
资源简介：
In high-dimensional regressions with low signal-to-noise ratios, we assess the predictive performance of several prevalent machine learning methods. Theoretical insights show Ridge regression's superiority in exploiting weak signals, surpassing a zero benchmark. In contrast, Lasso fails to exceed
提供机构：
美国国家经济研究局
创建时间：
2025-02-01
