Unverified50% confidenceFactExact time
Spatial correlation reduces the advantage of weight sharing: the asymptotic error of the convolutional student rises as the input spatial correlation c increases, whereas the asymptotic error of the locally connected student is independent of c and is overall lower at the same learning rate.
1
Sources
50%
Confidence
Long-term
Relevance
10/22/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedUnder correlated inputs, forcing weight sharing may introduce bias, causing the convolutional student to fail to fully recover the teacher parameters even with infinite data, whereas the locally connected network, by not sharing weights, can adapt more flexibly to the data.74% similarVerifiedDuring cross-domain fine-tuning, an excessively large learning rate will destroy pre-trained weights, while an excessively small one will result in almost no learning, requiring a careful trade-off.67% similarUnverified当目标数据域与源数据域差异悬殊时，预训练权重可能产生负迁移（Negative Transfer），反而干扰目标域的学习66% similarUnverifiedThe effectiveness of traditional ensemble learning depends on the errors among base learners being mutually independent; when error patterns are highly correlated, the ensemble benefit shrinks significantly.66% similarUnverifiedThe more aggressively the number of steps is compressed during distillation, the larger the distribution gap between the student model and the teacher model, and the greater the risk of detail loss and reduced image diversity.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1083912API
curl https://kongchang.com/api/v1/knowledge/claims/1083912MCP
get_claim(id=1083912)