AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

Optimal Transport under Group Fairness Constraints

Linus Bleistein, Mathieu Dagréou, Francisco Andrade, Thomas Boudou, Aurélien Bellet

ICML 2026 · Learning theory and algorithms › Optimal transport · approach: Sinkhorn and entropic OT algorithms · 0 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
relax exact fairness with a penalty (penalized OT) instead of FairSinkhornFairSinkhorn · Gaussian synthetictransport cost vs fairnessImproved
enforce exact fairness with FairSinkhorn instead of vanilla SinkhornSinkhorn · Gaussian synthetictransport costHurt
use penalized OT instead of cost learningcost learning · Circles syntheticcost-fairness trade-offImproved
use penalized OT instead of cost learningcost learning · Gaussian syntheticcost-fairness trade-offNo clear effect
use MLP cost instead of Mahalanobis cost (ablation)cost learning · Circles syntheticfairness loss: Mahalanobis cannot go below 10^-2Improved
increase entropic regularization epsilon in vanilla OTvanilla entropic OT · Gaussian and Circles syntheticfairnessNo clear effect
reuse learned cost instead of solving penalized OT for new samplespenalized OT · Gaussian synthetic (500 test samples)inference timeImproved
use learned cost instead of vanilla OT on unseen samplesvanilla OT · Gaussian synthetic (500 test samples)fairness lossImproved
use MLP cost instead of Mahalanobis cost on unseen samples (ablation)cost learning · Gaussian synthetic (500 test samples)fairness generalization gapHurt
compare penalized OT with cost learning with 7 income groupspenalized OT · Dating app (semi-synthetic)cost-fairness trade-offNo clear effect

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