AI Paper Atlas

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

Learning with Labeling Induced Abstentions

Kareem Amin, Giulia DeSalvo, Afshin Rostamizadeh

NeurIPS 2021 · Learning theory and algorithms › Prediction and decision losses · approach: Data attribution and recourse · 0 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 mixture requester (KNN + margin) instead of margin requesterDPL-Simplified · 10 binary datasetsonline mistakes / conditional test error: MIX better on 8 of 10 datasetsImproved
MIX vs margin requester on cod-rnaDPL-Simplified · cod-rnaonline mistakes: 360 ± 13 -> 329 ± 12Improved
MIX vs margin requester on cod-rnaDPL-Simplified · cod-rnaconditional test error (%): 2.2 ± 0.06 -> 1.5 ± 0.07Improved
MIX vs margin requester on ijcnnDPL-Simplified · ijcnnconditional test error (%): 2.4 ± 0.16 -> 0.7 ± 0.14Improved
MIX vs margin requester on skinDPL-Simplified · skinonline mistakes: 662 ± 110 -> 36 ± 31Improved
MIX vs margin requester on HIGGSDPL-Simplified · HIGGSonline mistakes: 5500 ± 90 -> 5689 ± 69Hurt
MIX vs margin requester on a9aDPL-Simplified · a9aconditional test error (%): 8.9 ± 0.44 -> 10.3 ± 0.30Hurt
MIX vs margin requester on cifarDPL-Simplified · cifarconditional test error (%): 5.1 ± 0.14 -> 3.8 ± 0.09Improved
MIX vs KNN requester on a9aDPL-Simplified · a9aonline mistakes: 2017 ± 35 -> 1713 ± 51Improved
MIX vs KNN requester on HIGGSDPL-Simplified · HIGGSconditional test error (%): 35.2 ± 0.31 -> 34.0 ± 0.27Improved
MIX vs margin requester on shuttleDPL-Simplified · shuttleconditional test error (%): 0.8 ± 0.09 -> 0.1 ± 0.05Improved
replace non-trivial requester r_t with uniform random requester (ablation)DPL-IWAL · six LIBSVM datasets, online mistakes and conditional lossonline mistakes / conditional lossHurt

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