Stability in Prediction Results
How much the loss changes when a single data point is modified.
The more loss is insensitive to data changes, the smaller the gap between empirical risk and true risk becomes, ensuring generalization performance
Loss Sensitivity
Creator
Creator
Seonglae ChoCreated
Created
2025 Jun 2 11:15Editor
Editor
Seonglae ChoEdited
Edited
2025 Jun 2 11:19Refs