Score: 0

Meta Optimality for Demographic Parity Constrained Regression via Post-Processing

Published: June 16, 2025 | arXiv ID: 2506.13947v1

By: Kazuto Fukuchi

Potential Business Impact:

Makes computer predictions fair for everyone.

Business Areas:
Predictive Analytics Artificial Intelligence, Data and Analytics, Software

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.

Country of Origin
🇯🇵 Japan

Page Count
29 pages

Category
Statistics:
Machine Learning (Stat)