Unverified50% confidenceFactExact time
In adversarial training, loss sharpness can exhibit two-stage dynamics, differing from the edge stability behavior observed in standard training.
1
Sources
50%
Confidence
Long-term
Relevance
11/6/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe change in gradient routing may affect training stability, especially when the loss surface is steeper in the early stage of training, and it is recommended to start with small-scale experiments for validation.79% similarVerifiedDuring the post-training phase, an excessively low loss may correspond to overfitting, where the model memorizes the training data and loses generalization ability.78% similarUnverifiedAfter adding the DINO objective, CAPI's originally smooth training loss curve became noticeably more erratic, and training stability decreased.78% similarUnverifiedTraining process monitoring detects anomalies by detecting sudden changes in loss curves, gradient anomalies, and so on, but backdoor implantation is often difficult to distinguish from normal training.76% similarUnverifiedThe traditional MoE load balancing loss mainly starts from training stability, making expert usage more uniform.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1142252API
curl https://kongchang.com/api/v1/knowledge/claims/1142252MCP
get_claim(id=1142252)