mlsanityData to 14 Oct 2026

A Comprehensive View of Fairness through Distributional Stability

arXiv 2609.37061 ↗First posted 29 Sep 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

We view fairness as a property of distributional stability. Rather than assessing a predictor under a fixed data distribution, we study how its predictions change under perturbations that modify the composition of protected groups. A predictor is fair if it remains stable under such shifts. Under this perspective, several classical notions of fairness arise as stability with respect to specific perturbations, with the associated unfairness gap given by a Lipschitz constant of a prediction-rate functional. This formulation also yields guarantees that hold uniformly over a range of demographic compositions at test time, without requiring knowledge of the deployment distribution. It leads to a learning procedure based on convex combinations of reweighted predictors, formulated as a second-order cone program, for which we establish generalization bounds. Experiments on standard benchmarks illustrate the approach.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 35 references that are in the map. First posted on arXiv 29 Sep 2026.

Builds on

16 of 35 references.

References · 16

  1. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  2. 2018A Reductions Approach to Fair Classificationcited by 587
  3. 2021Retiring Adult: New Datasets for Fair Machine Learningcited by 449
  4. 2018Classification with Fairness Constraints: A Meta-Algorithm with Provable Guaranteescited by 146
  5. 2020A survey on domain adaptation theory: learning bounds and theoretical guaranteescited by 109
  6. 2022Fair and Optimal Classification via Post-Processingcited by 51
  7. 2022Fair learning with Wasserstein barycenters for non-decomposable performance measurescited by 24
  8. 2019General Fair Empirical Risk Minimizationcited by 23
  9. 2023Bagging Provides Assumption-free Stabilitycited by 19
  10. 2022Fair Bayes-Optimal Classifiers Under Predictive Paritycited by 16
  11. 2023Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approachcited by 12
  12. 2024On the Inductive Biases of Demographic Parity-based Fair Learning Algorithmscited by 5
4 more
  1. 2023On the Vulnerability of Fairness Constrained Learning to Malicious Noisecited by 3
  2. 2024Finite-Sample and Distribution-Free Fair Classification: Optimal Trade-off Between Excess Risk and Fairness, and the Cost of Group-Blindnesscited by 3
  3. 2025Fair Text Classification via Transferable Representationscited by 3
  4. 2025Randomized multi-class classification under system constraints: a unified approach via post-processingcited by 1

Built on by

Not cited yet.