Unverified50% confidenceFactExact time
Scaling laws describe the empirical regularity that model loss decreases as a power law with parameter count, data volume, and compute.
1
Sources
50%
Confidence
Long-term
Relevance
10/25/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedScaling Laws表明模型的交叉熵损失会随着计算量、数据量和参数量的增加而平滑下降，且这种下降关系可以用简单的幂律函数精确拟合74% similarUnverifiedWeight decay adds a penalty term proportional to the square of the weights to the loss function, shrinking the weights toward zero and thereby limiting the model's effective capacity.71% similarUnverifiedScaling Laws describe the decrease in pre-training loss, not a linear improvement in all downstream capabilities; some capabilities, such as complex reasoning, exhibit emergent properties.70% similarUnverifiedThe academic community generally believes that mass loss is one of the core factors explaining the gap between models and observations, but the quantitative details still await research.69% similarUnverified2018年Wachter等人将反事实解释形式化为可计算的损失函数：最小化特征变化量的同时约束模型输出翻转到期望类别68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1097298API
curl https://kongchang.com/api/v1/knowledge/claims/1097298MCP
get_claim(id=1097298)