Meta Optimality for Demographic Parity Constrained Regression via Post-Processing
Not on the map. Why?
Abstract (arXiv)
We address the regression problem under the constraint of demographic parity, a commonly used fairness definition. Recent studies have revealed fair minimax optimal regression algorithms, the most accurate algorithms that adhere to the fairness constraint. However, these analyses are tightly coupled with specific data generation models. In this paper, we provide meta-theorems that can be applied to various situations to validate the fair minimax optimality of the corresponding regression algorithms. Furthermore, we demonstrate that fair minimax optimal regression can be achieved through post-processing methods, allowing researchers and practitioners to focus on improving conventional regression techniques, which can then be efficiently adapted for fair regression.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 31 of its 48 references that are in the map. First posted on arXiv 16 Jun 2025.
Builds on
31 of 48 references.
References · 31
- 2016Equality of Opportunity in Supervised Learningcited by 2,007
- 2014Certifying and removing disparate impactcited by 715
- 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
- 2016Inherent Trade-Offs in the Fair Determination of Risk Scorescited by 586
- 2017Nonparametric regression using deep neural networks with ReLU activation functioncited by 433
- 2018Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionalitycited by 162
- 2019Inherent Tradeoffs in Learning Fair Representationscited by 144
- 2019Wasserstein Fair Classificationcited by 131
- 2021Fair Mixup: Fairness via Interpolationcited by 109
- 2018Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goalscited by 103
- 2020Fair Regression with Wasserstein Barycenterscited by 100
- 2021Entropic estimation of optimal transport mapscited by 90
19 more
- 2021Plugin Estimation of Smooth Optimal Transport Mapscited by 68
- 2021Fairness via Representation Neutralizationcited by 63
- 2019Leveraging Labeled and Unlabeled Data for Consistent Fair Binary Classificationcited by 60
- 2021Rates of Estimation of Optimal Transport Maps using Plug-in Estimators via Barycentric Projectionscited by 53
- 2021Continuous Wasserstein-2 Barycenter Estimation without Minimax Optimizationcited by 51
- 2022Fair and Optimal Classification via Post-Processingcited by 51
- 2020Scalable Computations of Wasserstein Barycenter via Input Convex Neural Networkscited by 50
- 2019Deep learning is adaptive to intrinsic dimensionality of model smoothness in anisotropic Besov spacecited by 46
- 2021Classification with abstention but without disparitiescited by 28
- 2022Wasserstein Iterative Networks for Barycenter Estimationcited by 23
- 2022FARE: Provably Fair Representation Learning with Practical Certificatescited by 21
- 2022Optimal transport map estimation in general function spacescited by 20
- 2023Minimax estimation of discontinuous optimal transport maps: The semi-discrete casecited by 20
- 2022An improved central limit theorem and fast convergence rates for entropic transportation costscited by 18
- 2023Post-hoc Bias Scoring Is Optimal For Fair Classificationcited by 14
- 2022Fair Data Representation for Machine Learning at the Pareto Frontiercited by 12
- 2023Loss Balancing for Fair Supervised Learningcited by 11
- 2022Demographic Parity Constrained Minimax Optimal Regression under Linear Modelcited by 6
- 2024Minimax Optimal Fair Classification with Bounded Demographic Disparitycited by 3
Built on by
Citing papers per year: 2026: 2.
2 papers.