Unverified50% confidenceFactExact time
The double descent phenomenon occurs not only along the model size dimension, but can also appear with changes in training epochs and data volume.
1
Sources
50%
Confidence
Long-term
Relevance
8/6/2026
First Seen
Sources
Related Claims
VerifiedThe double descent phenomenon indicates that when the number of model parameters far exceeds the amount of data, the test error may actually decrease again.79% similarUnverifiedThe understanding of text-to-image models is essentially large-scale statistical association, and generation quality drops significantly when dealing with long-tail concepts that appear rarely in the training set.78% similarUnverifiedOpenAI在2019年的研究中证实双重下降现象同时存在于模型复杂度、训练时间和样本数量三个维度76% similarUnverifiedOn convergent tasks, there is a clear performance saturation phenomenon after models reach a certain scale, where continued increases in parameter count or training data yield rapidly diminishing marginal contributions to accuracy.75% similarUnverifiedThe marginal returns of simply increasing model parameters and training data are diminishing, a phenomenon known as 'Scaling Law slowdown.'75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/694693API
curl https://kongchang.com/api/v1/knowledge/claims/694693MCP
get_claim(id=694693)