Showing 2025Show all
2 papers · 1 filter
cs.LG2025
Rethinking Calibration for Early-Exit Neural Networks
Piotr Kubaty, Filip Szatkowski, Grzegorz Choczyński +2
Early-exit neural networks (EENNs) accelerate inference by allowing intermediate classifiers to stop computation once predictions are confident enough. Most methods rely on confide…
stat.ML2025
On Continuous Monitoring of Risk Violations under Unknown Shift
Alexander Timans, Rajeev Verma, Eric Nalisnick +1
Machine learning systems deployed in the real world must operate under dynamic and often unpredictable distribution shifts. This challenges the validity of statistical safety assur…