Pith. sign in

REVIEW 1 cited by

Loss Minimization Yields Multicalibration for Large Neural Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2304.09424 v2 pith:WBCDH5NP submitted 2023-04-19 cs.LG cs.AIstat.ML

classification cs.LGcs.AIstat.ML
keywords multicalibrationneurallosspredictorsminimizationnetworkssizewere
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Discretization-free Multicalibration through Loss Minimization over Tree Ensembles

    cs.LG 2025-05 conditional novelty 6.0 of 10

    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.

Pith tools