The implicit fairness criterion of unconstrained learning

Abstract

We clarify what fairness guarantees we can and cannot expect to follow from unconstrained machine learning. Specifically, we characterize when unconstrained learning on its own implies group calibration, that is, the outcome variable is conditionally independent of group membership given the score. We show that under reasonable conditions, the deviation from satisfying group calibration is upper bounded by the excess risk of the learned score relative to the Bayes optimal score function. A lower bound confirms the optimality of our upper bound. Moreover, we prove that as the excess risk of the learned score decreases, it strongly violates separation and independence, two other standard fairness criteria. Our results show that group calibration is the fairness criterion that unconstrained learning implicitly favors. On the one hand, this means that calibration is often satisfied on its own without the need for active intervention, albeit at the cost of violating other criteria that are at odds with calibration. On the other hand, it suggests that we should be satisfied with calibration as a fairness criterion only if we are at ease with the use of unconstrained machine learning in a given application.

37 pages, 9 figures

Cited by in corpus (17)

• Fairness in Machine Learning: A Survey
• An Empirical Characterization of Fair Machine Learning For Clinical Risk Prediction
• Verified Uncertainty Calibration
• FACT: A Diagnostic for Group Fairness Trade-offs
• Assessing Generalization of SGD via Disagreement
• Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification
• Environment Inference for Invariant Learning
• Sample Complexity of Uniform Convergence for Multicalibration
• Evaluation of Fairness Trade-offs in Predicting Student Success
• Uncertain Decisions Facilitate Better Preference Learning
• Algorithm Fairness in AI for Medicine and Healthcare
• Balancing Competing Objectives with Noisy Data: Score-Based Classifiers for Welfare-Aware Machine Learning
• Understanding the Under-Coverage Bias in Uncertainty Estimation
• Explaining generalization in deep learning: progress and fundamental limits
• MABR: Multilayer Adversarial Bias Removal Without Prior Bias Knowledge
• The Fair Game: Auditing & Debiasing AI Algorithms Over Time
• A Sociotechnical View of Algorithmic Fairness