AI Paper Atlas

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

Distribution-Free Statistical Dispersion Control for Societal Applications

Zhun Deng, Thomas P Zollo, Jake Snell, Toniann Pitassi, Richard Zemel

NeurIPS 2023 · Learning theory and algorithms › Prediction and decision losses · approach: Losses for decision-making · 1 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
Numerical optimization (NN-Opt.) instead of Berk-Jones bound (ablation)bound method · CivilComments group objective n=100bound on max difference in group medians: 0.07549 -> 0.01612Improved
NN-Opt. instead of Berk-Jones (ablation)bound method · CivilComments group objective n=100total objective bound: 0.42081 -> 0.34281Improved
NN-Opt. instead of Berk-Jones (ablation)bound method · CivilComments group objective n=200total objective bound: 0.31831 -> 0.30911Improved
NN-Opt. instead of Berk-Jones (ablation)bound method · CivilComments group objective n=200bound on max difference in group medians: 0.00666 -> 0.00292Improved
NN-Opt. instead of DKW (ablation)bound method · CivilComments group objective n=100total objective bound: 1.27645 -> 0.34281Improved
Increase samples per group from 100 to 200NN-Opt. · CivilComments group objectivetotal objective bound: 0.34281 -> 0.30911Improved
NN-Opt. instead of Berk-Jones for CVaR (ablation)bound method · CivilComments black female n=100CVaR bound: 0.91166 -> 0.85549Improved
NN-Opt. instead of Truncated Berk-Jones for CVaR (ablation)bound method · CivilComments black female n=100CVaR bound: 0.86379 -> 0.85549Improved
NN-Opt. instead of Berk-Jones for VaR-Interval (ablation)bound method · CivilComments black female n=100VaR-Interval bound: 0.38057 -> 0.32656Improved
NN-Opt. instead of Berk-Jones for smoothed median (ablation)bound method · CivilComments black female n=100Smoothed-Median bound: 0.00038 -> 0.00021Improved
NN-Opt. adapted to CVaR instead of Berk-Jones, bound on expected loss (ablation)bound method · CivilComments black female n=100expected loss bound: 0.25 -> 0.23Improved
Truncated Berk-Jones instead of Berk-Jones, expected loss bound (ablation)Berk-Jones · CivilComments black female n=100expected loss bound: 0.25 -> 0.50Hurt

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