3 accepted papers
Modern neural networks can be accurate yet poorly calibrated. We present Random Geometric Calibration (RGC), a post hoc method that augments confidence estimation with a geometric signal derived from distances to training data in an aggregated semantic representation space. Prior geometric calibrati
Machine learning classifiers are probabilistic in nature, and thus inevitably involve uncertainty. Predicting the probability of a specific input to be correct is called uncertainty (or confidence) estimation and is crucial for risk management.Post-hoc model calibrations can improve models’ uncertai…
Conflict-Based Search (CBS) is a leading algorithm for optimal Multi-Agent Path Finding (MAPF). CBS variants typically compute MAPF solutions using some form of A* search. However, they often do so under strict time limits so as to avoid exhausting the available memory. In this paper, we present IDC…