AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraints

Andrew Cotter, Maya Gupta, Heinrich Jiang, Nathan Srebro, Karthik Sridharan, Serena Wang, Blake Woodworth, Seungil You

ICML 2019 · Learning theory and algorithms › Fairness · approach: Fairness-constrained classification · 15 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 an independent validation set to choose constraint multipliers instead of using the same data for model and constraint updatesPracticalTwoDataset on Communities and Crime · Communities and CrimeMaximum constraint violation: $.022$ -> $-.008$Improved
Use an independent validation set to choose constraint multipliers instead of using the same data for model and constraint updatesPracticalTwoDataset on Adult · AdultMaximum constraint violation: $.011$ -> $.005$Improved
Use an independent validation set to choose constraint multipliers instead of using the same data for model and constraint updatesPracticalTwoDataset on COMPAS · COMPASMaximum constraint violation: $.038$ -> $.004$Improved
Use an independent validation set to choose constraint multipliers instead of using the same data for model and constraint updatesPracticalTwoDataset on Business Entity Resolution · Business Entity ResolutionMaximum constraint violation: $.073$ -> $.072$No clear effect
Use an independent validation set to choose constraint multipliers instead of using the same data for model and constraint updatesPracticalTwoDataset on Adult · AdultError: $.156$ -> $.169$Hurt
Use an independent validation set to choose constraint multipliers instead of using the same data for model and constraint updatesPracticalTwoDataset on COMPAS · COMPASError: $.353$ -> $.378$Hurt
Use an independent validation set to choose constraint multipliers instead of using the same data for model and constraint updatesLagrangianTwoDataset on Communities and Crime · Communities and CrimeMaximum constraint violation: $.001$ -> $-.012$Improved
Use an independent validation set to choose constraint multipliers instead of using the same data for model and constraint updatesLagrangianTwoDataset on Adult · AdultMaximum constraint violation: $.013$ -> $.008$Improved
Use an independent validation set to choose constraint multipliers instead of using the same data for model and constraint updatesLagrangianTwoDataset on COMPAS · COMPASMaximum constraint violation: $.029$ -> $.006$Improved
Use an independent validation set to choose constraint multipliers instead of using the same data for model and constraint updatesLagrangianTwoDataset on Business Entity Resolution · Business Entity ResolutionMaximum constraint violation: $.042$ -> $.041$No clear effect
Use an independent validation set to choose constraint multipliers instead of using the same data for model and constraint updatesLagrangianTwoDataset on COMPAS · COMPASError: $.349$ -> $.378$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