AI Paper Atlas

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

ICLR 2022 · Learning theory and algorithms › Fairness · approach: Fairness-constrained classification · 2 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use distributionally robust fairness-aware PCA instead of FairPCAFairPCA · Biodeg out-of-sampleABDiff.: 27.5159 -> 23.0066Improved
Use distributionally robust fairness-aware PCA instead of FairPCAFairPCA · Biodeg out-of-sampleARE.: 34.6184 -> 33.8571Improved
Use distributionally robust fairness-aware PCA instead of FairPCAFairPCA · Energy out-of-sampleABDiff.: 0.0138 -> 0.0125Improved
Use distributionally robust fairness-aware PCA instead of FairPCAFairPCA · Energy out-of-sampleARE.: 0.2225 -> 0.2238Hurt
Use distributionally robust fairness-aware PCA instead of FairPCAFairPCA · German Credit out-of-sampleABDiff.: 1.3670 -> 2.0588Hurt
Use distributionally robust fairness-aware PCA instead of FairPCAFairPCA · German Credit out-of-sampleARE.: 44.0064 -> 43.9032Improved
Use distributionally robust fairness-aware PCA instead of FairPCAFairPCA · Image out-of-sampleABDiff.: 1.6129 -> 0.7522Improved
Use distributionally robust fairness-aware PCA instead of FairPCAFairPCA · Image out-of-sampleARE.: 10.2616 -> 6.0199Improved
Use RFPCA instead of CFPCA-Mean Con.CFPCA-Mean Con. · Default Credit out-of-sampleABDiff.: 0.9367 -> 0.9483Hurt
Use RFPCA instead of FairPCAFairPCA · Default Credit out-of-sampleARE.: 10.4439 -> 10.3995Improved
Increase the ambiguity-set radius from small valuesRFPCA · Toy Gaussian dataARE. + ABDiff.Mixed
Set the ambiguity-set radius too largeRFPCA · Toy Gaussian dataARE. + ABDiff.Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy