Exact convex calibration of the multi-label Jaccard loss requires dimension exponential in the label count, while any fixed additive regret tolerance is achievable in polynomial dimension.
Calibrated surrogate maximization of linear-fractional utility in binary classification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Exponential Convex Calibration Dimension for the Multi-Label Jaccard Measure
Exact convex calibration of the multi-label Jaccard loss requires dimension exponential in the label count, while any fixed additive regret tolerance is achievable in polynomial dimension.