AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

The Price of Fair PCA: One Extra dimension

Samira Samadi, Uthaipon Tantipongpipat, Jamie H Morgenstern, Mohit Singh, Santosh Vempala

NeurIPS 2018 · Learning theory and algorithms › Sample complexity · approach: Generalization and limits under data constraints · 77 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 vanilla PCA instead of Fair PCALFW (gender groups) · LFWaverage reconstruction lossHurt
Use Fair PCA instead of vanilla PCALFW (gender groups) · LFWaverage reconstruction lossMixed
Use vanilla PCA instead of Fair PCADefault Credit (education groups) · Default Creditaverage reconstruction lossMixed
Use Fair PCA to balance the groups' additional average reconstruction lossFair PCA · LFW and Default Creditaverage reconstruction lossMixed
Allow one extra dimension in the output embeddingFair PCA for two groups · Fair PCA objectivemaximum normalized additional reconstruction lossImproved

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