Interpolation Learning With Minimum Description Length
arxiv(2023)
摘要
We prove that the Minimum Description Length learning rule exhibits tempered overfitting. We obtain tempered agnostic finite sample learning guarantees and characterize the asymptotic behavior in the presence of random label noise.
更多查看译文
关键词
interpolation,learning,description
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要