Research map / Learning theory and algorithms / Fairness
Correcting Overparameterization Effects in Fair Empirical Risk Minimization
Xiaoyi MAI, Jean-Michel Loubes
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| increase overcompensation hyperparameter omega above 0 in fair ERM (ablation) | kernel fair ERM with logistic loss · synthetic data, n = 500, p = 4n | gap in group true/false positive rates | Improved |
| classical fair ERM (omega = 0) as p/n grows (ablation) | kernel fair ERM · synthetic data and Color-MNIST | group TPR/FPR gap | Hurt |
| use overcompensation method (Algorithm 1) instead of classical fair ERM | kernel fair ERM · synthetic data and Color-MNIST | accuracy and equalized odds | Improved |
| impose balanced coefficients as an optimization constraint (Eq. 15) (ablation) | kernel fair ERM · synthetic data (same as Figure 3) | equalized odds | Hurt |
Closest papers by meaning
- Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective (ICML 2025 · similarity 0.87)
- f-FERM: A Scalable Framework for Robust Fair Empirical Risk Minimization (ICLR 2024 · similarity 0.87)
- Fairness without Harm: An Influence-Guided Active Sampling Approach (NeurIPS 2024 · similarity 0.86)
- The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning (NeurIPS 2024 · similarity 0.86)
- Kernel-based Equalized Odds: A Quantification of Accuracy-Fairness Trade-off in Fair Representation Learning (NeurIPS 2025 · similarity 0.85)
- Learning with Statistical Equality Constraints (NeurIPS 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
