Loss Minimization Yields Multicalibration for Large Neural Networks
OPEN ACCESS
Loading...
Author / Producer
Date
2024
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
OPEN ACCESS
Data
Rights / License
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.
Permanent link
Publication status
published
External links
Book title
15th Innovations in Theoretical Computer Science Conference (ITCS 2024)
Volume
287
Pages / Article No.
Publisher
Schloss Dagstuhl – Leibniz-Zentrum für Informatik
Event
15th Innovations in Theoretical Computer Science Conference (ITCS 2024)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Multi-group fairness; loss minimization; neural networks
Organisational unit
09622 - Steurer, David / Steurer, David