Research map / Learning theory and algorithms / Optimal transport
Obtaining Fairness using Optimal Transport Theory
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use Random Repair instead of Geometric Repair at the amount needed to reach the DI confidence-interval threshold | Logit on Adult Income · Adult Income test set | misclassification error: 0.2136 -> 0.2068 | Helped |
| Use Random Repair instead of Geometric Repair at the amount needed to reach the DI confidence-interval threshold | Random Forests on Adult Income · Adult Income test set | misclassification error: 0.2076 -> 0.1927 | Helped |
| Replace unmodified data with repair procedure B | Logit · Adult Income test set | Disparate Impact: 0.496 -> 1 | Helped |
| Replace unmodified data with repair procedure B | Random Forests · Adult Income test set | Disparate Impact: 0.484 -> 1 | Helped |
| Use repair procedure B instead of A | Logit · Adult Income test set | misclassification error: 0.218 -> 0.2077 | Helped |
| Use repair procedure B instead of A | Random Forests · Adult Income test set | misclassification error: 0.2272 -> 0.2045 | Helped |
| Replace repair procedure A with per-attribute repair procedure C | Logit · Adult Income test set | misclassification error: 0.218 -> 0.2132 | Helped |
| Replace repair procedure A with per-attribute repair procedure C | Random Forests · Adult Income test set | misclassification error: 0.2272 -> 0.2152 | Helped |
| Replace full repair with Geometric Repair along the Wasserstein geodesic | Logit on Adult Income · Adult Income test set | misclassification error: 0.2068 -> 0.2136 | Hurt |
Closest papers by meaning
- A Comprehensive View of Fairness through Distributional Stability (NeurIPS 2026 · similarity 0.86)
- Geometry of Relaxed Fair Regression: A Unified Framework for Aware and Unaware Settings (NeurIPS 2026 · similarity 0.85)
- Sequential Conditional Transport on Probabilistic Graphs for Interpretable Counterfactual Fairness (AAAI 2025 · similarity 0.84)
- Demographic parity in regression and classification within the unawareness framework (NeurIPS 2026 · similarity 0.84)
- Reconciling Predictive and Statistical Parity: A Causal Approach (AAAI 2024 · similarity 0.84)
- Efficient Fairness-Performance Pareto Front Computation (NeurIPS 2025 · similarity 0.84)
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.