Research map / Learning theory and algorithms / Fairness
Distributionally Robust Fair Principal Components via Geodesic Descents
Hieu Vu, Toan Tran, Man-Chung Yue, Viet Anh Nguyen
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 |
|---|---|---|---|
| Use distributionally robust fairness-aware PCA instead of FairPCA | FairPCA · Biodeg out-of-sample | ABDiff.: 27.5159 -> 23.0066 | Improved |
| Use distributionally robust fairness-aware PCA instead of FairPCA | FairPCA · Biodeg out-of-sample | ARE.: 34.6184 -> 33.8571 | Improved |
| Use distributionally robust fairness-aware PCA instead of FairPCA | FairPCA · Energy out-of-sample | ABDiff.: 0.0138 -> 0.0125 | Improved |
| Use distributionally robust fairness-aware PCA instead of FairPCA | FairPCA · Energy out-of-sample | ARE.: 0.2225 -> 0.2238 | Hurt |
| Use distributionally robust fairness-aware PCA instead of FairPCA | FairPCA · German Credit out-of-sample | ABDiff.: 1.3670 -> 2.0588 | Hurt |
| Use distributionally robust fairness-aware PCA instead of FairPCA | FairPCA · German Credit out-of-sample | ARE.: 44.0064 -> 43.9032 | Improved |
| Use distributionally robust fairness-aware PCA instead of FairPCA | FairPCA · Image out-of-sample | ABDiff.: 1.6129 -> 0.7522 | Improved |
| Use distributionally robust fairness-aware PCA instead of FairPCA | FairPCA · Image out-of-sample | ARE.: 10.2616 -> 6.0199 | Improved |
| Use RFPCA instead of CFPCA-Mean Con. | CFPCA-Mean Con. · Default Credit out-of-sample | ABDiff.: 0.9367 -> 0.9483 | Hurt |
| Use RFPCA instead of FairPCA | FairPCA · Default Credit out-of-sample | ARE.: 10.4439 -> 10.3995 | Improved |
| Increase the ambiguity-set radius from small values | RFPCA · Toy Gaussian data | ARE. + ABDiff. | Mixed |
| Set the ambiguity-set radius too large | RFPCA · Toy Gaussian data | ARE. + ABDiff. | Hurt |
Closest papers by meaning
- Fast and Efficient MMD-Based Fair PCA via Optimization over Stiefel Manifold (AAAI 2022 · similarity 0.90)
- Convex Formulations for Fair Principal Component Analysis (AAAI 2019 · similarity 0.87)
- Manifold denoising by Nonlinear Robust Principal Component Analysis (NeurIPS 2019 · similarity 0.86)
- Fun with Flags: Robust Principal Directions via Flag Manifolds (CVPR 2024 · similarity 0.86)
- Multi-Criteria Dimensionality Reduction with Applications to Fairness (NeurIPS 2019 · similarity 0.86)
- Exact Guarantees on the Absence of Spurious Local Minima for Non-negative Rank-1 Robust Principal Component Analysis (JMLR 2020 · similarity 0.86)
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.
