AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

Fair Densities via Boosting the Sufficient Statistics of Exponential Families

Alexander Soen, Hisham Husain, Richard Nock

ICML 2023 · Learning theory and algorithms › Fairness · approach: Fairness-constrained classification

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
exact leverage (sr0=1) vs relative leverage (sr0=0.9) in FBDE (ablation)FBDE · COMPAS and AdultSR vs KL trade-off: COMPAS SR .988 vs .896; KL .135 vs .127Improved
FBDE boosting (preprocessing) versus Celis max-entropy baselineFBDE · Adult (S=sex)KL: 0.122 vs 0.182Improved
Celis max-entropy baseline vs FBDECelis · COMPAS and AdultSR: 0.992 / 0.979 vs ~0.96-0.99Improved
TabFairGAN pre-processingTabFairGAN · COMPAS and AdultSR and RR: COMPAS SR .727 with std .100; Adult KL 1.68Hurt
FBDE with relative leverage vs exact on continuous Minneapolis dataFBDE · Minneapolis (continuous)RR: RR 0.847 vs theoretical sqrt(tau) approx 0.894No clear effect
Decision tree WL based FBDE, data fairness (SR) on COMPASFBDE · COMPAS and Adultprediction fairness SR_clf: COMPAS SR_clf .959 for FBDE M_a; Adult .818 for FBDE M_a vs .919 for CelisMixed

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