A one-shot ERM over depth-two tree ensembles on the base predictor and group indicators yields multicalibration whenever squared loss is saturated, a condition verified empirically on six datasets.
Nuanced metrics for measuring unintended bias with real data for text classification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Discretization-free Multicalibration through Loss Minimization over Tree Ensembles
A one-shot ERM over depth-two tree ensembles on the base predictor and group indicators yields multicalibration whenever squared loss is saturated, a condition verified empirically on six datasets.