Research map / Learning theory and algorithms / Optimal transport
A General Approach to Fairness with Optimal Transport
Chiappa Silvia, Jiang Ray, Stepleton Tom, Pacchiano Aldo, Jiang Heinrich, Aslanides John
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 |
|---|---|---|---|
| add Wass-2 geodesic output transport (t=1) versus unconstrained | linear regression · NLSY | nWass2: 4.870 -> 0.090 | Improved |
| add Wass-2 geodesic output transport (t=1) versus unconstrained | linear regression · NLSY | MSE: 1.210 -> 1.374 | Hurt |
| add Wass-2 geodesic output transport (t=1) versus unconstrained | linear regression · Communities & Crime | nWass2: 51.857 -> 0.902 | Improved |
| add Wass-2 geodesic output transport (t=1) versus unconstrained | linear regression · LSAC | nWass2: 3.761 -> 0.036 | Improved |
| Wass-2 penalty instead of MMD penalty | linear regression · LSAC | nWass2: 0.276 -> 0.279 | Mixed |
| Wass-2 Geo instead of Corr Penalty | linear regression · LSAC | MSE: 0.335 -> 0.211 | Improved |
| Wass-2 Geo instead of GF Lag | linear regression · Communities & Crime | nWass2: 35.340 -> 0.902 | Improved |
| Wass-2 penalty versus MMD penalty on Pareto frontier | linear regression · NLSY, C&C, LSAC | MSE vs nWass2 trade-off | Improved |
| add WCeps penalty for input transportation versus PSCC | logistic model · UCI Adult (PSCF) | nWass2: 0.977 -> 0.620 | Improved |
| add WCeps penalty for input transportation versus PSCC | logistic model · UCI Adult (PSCF) | Err-0.5: 0.195 -> 0.206 | Hurt |
Closest papers by meaning
- Optimal Transport under Group Fairness Constraints (ICML 2026 · similarity 0.91)
- Obtaining Fairness using Optimal Transport Theory (ICML 2019 · similarity 0.90)
- A Comprehensive View of Fairness through Distributional Stability (NeurIPS 2026 · similarity 0.87)
- Sequential Conditional Transport on Probabilistic Graphs for Interpretable Counterfactual Fairness (AAAI 2025 · similarity 0.87)
- Geometry of Relaxed Fair Regression: A Unified Framework for Aware and Unaware Settings (NeurIPS 2026 · similarity 0.87)
- Efficient Fairness-Performance Pareto Front Computation (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.
