Unverified60% confidenceFactExact time
The double descent phenomenon was systematically proposed and named by Mikhail Belkin and other researchers around 2019
2
Sources
60%
Confidence
Long-term
Relevance
7/12/2026
First Seen
Sources
The Theory of Deep Learning: Why Do Neural Networks Work? A Complete Overview of Theoretical Research
hackernewshackernews7/11/2026
Related Claims
UnverifiedThe double descent phenomenon was systematically revealed by Belkin et al. in 2019, overturning the classical U-shaped test error curve.78% similarUnverifiedBelkin等人2019年提出调和插值框架，Bartlett等人2020年研究良性过拟合，从不同角度推进对双重下降的理解77% similarUnverified空洞卷积最初由Fisher Yu和Vladlen Koltun在2016年的语义分割研究中系统性引入64% similarUnverifiedThe spectral bias phenomenon was first systematically characterized by Xu et al. around 2019 through a large number of numerical experiments.60% similarUnverifiedModel Collapse was first systematically described by machine learning researcher Ilia Shumailov and colleagues in 2023 in the journal Nature.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/494294API
curl https://kongchang.com/api/v1/knowledge/claims/494294MCP
get_claim(id=494294)