Demographic Parity Constrained Minimax Optimal Regression under Linear Model

Kazuto Fukuchi; Jun Sakuma

NeurIPS 2023poster5 citations

Demographic Parity Constrained Minimax Optimal Regression under Linear Model

Abstract

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. Our analysis reveals that the minimax optimal error for the demographic parity-constrained regression problem under our model is characterized by $\Theta(\frac{dM}{n})$, 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.

demographic parityregressionminimax optimal

BibTeX

@inproceedings{
fukuchi2023demographic,
title={Demographic Parity Constrained Minimax Optimal Regression under Linear Model},
author={Kazuto Fukuchi and Jun Sakuma},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
year={2023},
url={https://openreview.net/forum?id=GrFsx4mBWF}
}