mlsanityData to 7 Oct 2026

Demographic Parity Constrained Minimax Optimal Regression under Linear Model

arXiv 2206.11546 ↗First posted 23 Jun 2022math.ST stat.ML stat.THcited by 6

Not on the map. Why?

Abstract (arXiv)

We explore the minimax optimal error associated with a demographic parity-constrained regression problem within the context of a linear model. Our proposed model encompasses a broader range of discriminatory bias sources compared to the model presented by Chzhen and Schreuder (2022). Our analysis reveals that the minimax optimal error for the demographic parity-constrained regression problem under our model is characterized by Theta(fracdMn), where n denotes the sample size, d represents the dimensionality, and M signifies the number of demographic groups arising from sensitive attributes. Moreover, we demonstrate that the minimax error increases in conjunction with a larger bias present in the model.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 8 of its 32 references that are in the map. First posted on arXiv 23 Jun 2022.

Builds on

8 of 32 references.

References · 8

  1. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  2. 2018A Reductions Approach to Fair Classificationcited by 585
  3. 2019Fair Regression: Quantitative Definitions and Reduction-based Algorithmscited by 168
  4. 2017Controllable Invariance through Adversarial Feature Learningcited by 127
  5. 2018Invariant Representations without Adversarial Trainingcited by 111
  6. 2020Fair Regression with Wasserstein Barycenterscited by 99
  7. 2019Pairwise Fairness for Ranking and Regressioncited by 58
  8. 2019Exact minimax risk for linear least squares, and the lower tail of sample covariance matricescited by 34

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 2; 2026: 1.

6 papers.

  1. 2024On the Maximal Local Disparity of Fairness-Aware Classifierscited by 3
  2. 2025Meta Optimality for Demographic Parity Constrained Regression via Post-Processingcited by 2
  3. 2024Auditing and Enforcing Conditional Fairness via Optimal Transportcited by 1
  4. 2025Learning Pareto manifolds in high dimensions: How can regularization help?cited by 1
  5. 2024Reducing Biases in Record Matching Through Scores Calibrationcited by 0
  6. 2026Fair Regression under Demographic Parity: A Unified Frameworkcited by 0