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.
Loss Minimization Yields Multicalibration for Large Neural Networks
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Multicalibration is a notion of fairness for predictors that requires them to provide calibrated predictions across a large set of protected groups. Multicalibration is known to be a distinct goal than loss minimization, even for simple predictors such as linear functions. In this work, we consider the setting where the protected groups can be represented by neural networks of size $k$, and the predictors are neural networks of size $n > k$. We show that minimizing the squared loss over all neural nets of size $n$ implies multicalibration for all but a bounded number of unlucky values of $n$. We also give evidence that our bound on the number of unlucky values is tight, given our proof technique. Previously, results of the flavor that loss minimization yields multicalibration were known only for predictors that were near the ground truth, hence were rather limited in applicability. Unlike these, our results rely on the expressivity of neural nets and utilize the representation of the predictor.
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.