2 papers
cs.LG2026
Entropy Minimization without Model Collapse: Mitigating Prediction Bias in Medical Imaging
Tim Nielen, Sameer Ambekar, Johannes Kiechle +2
Entropy minimization (EM) is the dominant objective for test-time adaptation, yet its failure mode, model collapse, remains poorly understood. In this work, we show that distributi…
cs.LG2025
Antithetic Sampling for Top-k Shapley Identification
Patrick Kolpaczki, Tim Nielen, Eyke Hüllermeier
Additive feature explanations rely primarily on game-theoretic notions such as the Shapley value by viewing features as cooperating players. The Shapley value's popularity in and o…