AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

An Information-Theoretic Quantification of Discrimination with Exempt Features

Sanghamitra Dutta, Praveen Venkatesh, Piotr Mardziel, Anupam Datta, Pulkit Grover

AAAI 2020 · Learning theory and algorithms › Prediction and decision losses · approach: Counterfactual explanations and recourse · 19 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
regularize with I(Z;Yhat|Xc) (L3) instead of I(Z;Yhat) (L2), lambda=4logistic regression classifier · Synthetic ad-targeting case studyaccuracy (%): 81.1 -> 89.6Improved
regularize with I(Z;Yhat|Xc) (L3) instead of I(Z;Yhat) (L2), lambda=10logistic regression classifier · Synthetic ad-targeting case studyaccuracy (%): 70.2 -> 80.8Improved
add conditional fairness regularizer (L3, lambda=4) to cross-entropylogistic regression classifier · Synthetic ad-targeting case studyaccuracy (%): 98.5 -> 89.6Hurt
increase lambda for L3 from 4 to 10logistic regression classifier · Synthetic ad-targeting case studyaccuracy (%): 89.6 -> 80.8Hurt

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