AI Paper Atlas

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

Top-Ambiguity Samples Matter: Understanding Why Deep Ensemble Works in Selective Classification

Qiang Ding, Yixuan Cao, Ping Luo

NeurIPS 2023 · Learning theory and algorithms › Prediction and decision losses · approach: Data attribution and recourse · 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
ensemble 5 members vs single member (Deep Ensemble)Deep Ensemble · CIFAR-10AURC/10^-4: 66.1±5.6 -> 51.2±2.0Improved
ensemble vs single member (Deep Ensemble)Deep Ensemble · CIFAR-100AURC/10^-4: 793.1±9.0 -> 672.5±1.9Improved
ensemble vs single member (Gambler)Gambler · CIFAR-100AURC/10^-4: 930.6±10.2 -> 857.1±4.7Improved
ensemble vs single member (Gambler)Gambler · SVHNAURC/10^-4: 44.2±2.5 -> 37.0±0.8Improved
ensemble only on top-50% ambiguity samples vs lowest-50% (ablation)Deep Ensemble · CIFAR/text datasetsselective riskImproved
ensemble only on low-ambiguity samples (ablation)Deep Ensemble · CIFAR/text datasetsselective riskNo clear effect
increase number of ensemble members (ablation)Deep Ensemble · CIFAR-10AURCImproved
ensemble of 4 VGG-16 vs a single Big VGG-16 of similar size (ablation)Deep Ensemble · CIFAR-10AURC/10^-4: 89.2 -> 49.3Improved
Deep Ensemble vs SAT ensemble on noisy-label datasetDeep Ensemble · SVHNAURC/10^-4: 32.4±0.9 -> 37.1±0.3Hurt
remove label noise from SVHN (ablation)Deep Ensemble · SVHNAURCImproved
Reg-curr ensemble vs Deep EnsembleReg-curr · MNLIAURC/10^-4: 465.2 ±3.8 -> 451.9 ±2.1Improved
Gambler ensemble vs Deep EnsembleGambler · MRPCAURC/10^-4: 561.3±55.6 -> 650.1±24.8Hurt

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