Generalization gap prediction on Stanford Cars
0.13Generalization Gap Prediction ErrorHessian
Evaluation Results
| Method | Links | |
|---|---|---|
| HessianTraining scenario=From scratch, Data source=Test loss landscape (dev data, unfair advantage)2023.05 | 0.13 | |
| InconsistencyTraining scenario=From scratch, Data source=Unlabeled data2023.05 | 0.15 | |
| 1-sharpnessTraining scenario=From scratch, Data source=Test loss landscape (dev data, unfair advantage)2023.05 | 0.72 | |
| HessianTraining scenario=From scratch, Data source=Training loss landscape2023.05 | 0.78 | |
| 1-sharpnessTraining scenario=From scratch, Data source=Training loss landscape2023.05 | 0.84 |