arXiv stat.ML
· Papers
Exponential Convex Calibration Dimension for the Multi-Label Jaccard Measure
arXiv:2608.13549v1 Announce Type: cross Abstract: The per-instance Jaccard score, or intersection over union (IoU), is standard in multi-label classification and binary segmentation. With $s$ labels, its loss matrix has $2^s$ outcomes and reports. Under the convention $mathrm{Jac}(varnothing,varnothing)=1$, we prove