AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

Certifying Some Distributional Fairness with Subpopulation Decomposition

Mintong Kang, Linyi Li, Maurice Weber, Yang Liu, Ce Zhang, Bo Li

NeurIPS 2022 · Learning theory and algorithms › Fairness · approach: Fairness auditing and regularization · 4 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
add non-skewness box constraint (smaller Delta_s) on the shifted distribution Q (ablation)fairness certificate (sensitive shifting) · Adultcertified error boundImproved
add fairness constraint and the subpopulation-decomposition optimization versus WRM distributional robustness boundfairness certificate · synthetic datasetcertified loss bound (JSD loss)Improved
switch from sensitive shifting to general shifting (extra shift within each subpopulation)fairness certificate · Adult, Compas, Health, Lawschoolcertification tightnessHurt
certify with sensitive shifting only (no change within subpopulations)fairness certificate · Adult, Compas, Health, Lawschool, Crime, Germanclassification error and BCE lossImproved
use very small distribution distance between P and Q with the fairness constraintfairness certificate · synthetic datasetfeasibility of certificateHurt
use large distribution shift with the fairness constraintfairness certificate · synthetic datasetcertified loss boundImproved

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