AI Paper Atlas

Research map / Learning theory and algorithms / Fairness

Fair regression via plug-in estimator and recalibration with statistical guarantees

Evgenii Chzhen, Christophe Denis, Mohamed Hebiri, Luca Oneto, Massimiliano Pontil

NeurIPS 2020 · Learning theory and algorithms › Fairness · approach: Minimax fairness via sampling

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 the proposed recalibration stepRandom Forest · CRIMEKS: .45 -> .09Improved
add the proposed recalibration stepRandom Forest · CRIMEMSE: .020 -> .031Hurt
add the proposed recalibration stepRandom Forest · LAWKS: .11 -> .03Improved
add the proposed recalibration stepRandom Forest · NLSYKS: .55 -> .05Improved
add the proposed recalibration stepRandom Forest · STUDKS: .45 -> .05Improved
add the proposed recalibration stepRandom Forest · STUDMSE: 3.59 -> 3.93Hurt
add the proposed recalibration stepRandom Forest · UNIVKS: .10 -> .02Improved
add the proposed recalibration stepKernel RLS · NLSYKS: .58 -> .05Improved
add the proposed recalibration stepKernel RLS · NLSYMSE: .061 -> .070Hurt
add the proposed recalibration stepRegularized least squares (linear) · NLSYKS: .73 -> .16Improved
add the proposed recalibration stepRegularized least squares (linear) · STUDKS: .50 -> .11Improved
replace the Agarwal et al. fairness reduction with the proposed recalibrationRandom Forest · CRIMEKS: .13 -> .09Improved

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