Our paper (K. Fukuchi, 2025), titled Meta Optimality for Demographic Parity Constrained Regression via Post-Processing, has been accepted at the 42th International Conference on Machine Learning (ICML 2025). This paper presents a post-processing approach and a general theoretical framework for achieving fair minimax optimal regression under the demographic parity constraint.

References

  1. Kazuto Fukuchi. Meta Optimality for Demographic Parity Constrained Regression via Post-Processing. Forty-second International Conference on Machine Learning, vol. 267, pp. 18024-18046, 2025.arXiv