论文标题
了解机器学习中的双重下降曲线
Understanding the double descent curve in Machine Learning
论文作者
论文摘要
在应用机器学习算法时，偏见变化的理论用作模型选择的指南。但是，现代实践显示出成功的模型，这些模型预计会过度合适，但却没有。这导致了Belkin等人的双重下降曲线的提议。尽管它似乎描述了一种真实的代表性现象，但该领域缺乏对正在发生的事情的基本理论理解，对模型选择的后果以及何时会发生双重下降。在本文中，我们对现象产生了有原则的理解，并为这些重要问题的答案绘制了答案。此外，我们报告了我们提出的假设正确预测的实际实验结果。
The theory of bias-variance used to serve as a guide for model selection when applying Machine Learning algorithms. However, modern practice has shown success with over-parameterized models that were expected to overfit but did not. This led to the proposal of the double descent curve of performance by Belkin et al. Although it seems to describe a real, representative phenomenon, the field is lacking a fundamental theoretical understanding of what is happening, what are the consequences for model selection and when is double descent expected to occur. In this paper we develop a principled understanding of the phenomenon, and sketch answers to these important questions. Furthermore, we report real experimental results that are correctly predicted by our proposed hypothesis.
