2 papers
cs.LG2026
OperatorSHAP: Fast and Accurate Shapley Value Estimation for Neural Operators
Joshua Stiller, Santo M. A. R. Thies, Felix Czaja +1
Understanding model predictions is essential for physical applications, where outputs often inform safety-critical decisions, such as structural load assessment, weather warnings,…
cs.LG2026
Decision-Aligned Evaluation of Uncertainty Quantification
Annika Schneider, Tommy Rochussen, Joshua Stiller +1
Uncertainty estimates in machine learning are typically evaluated using generic metrics such as the negative log-likelihood and expected calibration error, yet good performance on…