A ridge regression model trained solely on in-distribution score statistics predicts the AUC optimism gap under distribution shift for RF-impairment detectors, generalizing to unseen detectors (R²=0.47) and classes (R²=0.46) in simulation and showing smaller effects on real GNSS data.
Evaluation of (un-)supervised ma- chine learning methods for GNSS interference classification with real- world data discrepancies,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SP 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Anticipating the Optimism Gap: Predicting Distribution-Shift Degradation of RF-Impairment Detectors from In-Distribution Statistics
A ridge regression model trained solely on in-distribution score statistics predicts the AUC optimism gap under distribution shift for RF-impairment detectors, generalizing to unseen detectors (R²=0.47) and classes (R²=0.46) in simulation and showing smaller effects on real GNSS data.