AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Improving Simple Models with Confidence Profiles

Amit Dhurandhar, Karthikeyan Shanmugam, Ronny Luss, Peder A. Olsen

NeurIPS 2018 · Architectures and efficiency › RNNs and normalization · approach: Efficient network compression and training · 17 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
Weight CIFAR-10 simple ResNets with ProfWeight confidence profilesSM-3, SM-5, SM-7, and SM-9 · CIFAR-10 holdout testaccuracy: 73.15($\pm$ 0.7) -> 77.52 ($\pm$0.01); 75.78($\pm$0.5) -> 79.25($\pm$0.36); 78.76($\pm$0.35) -> 81.34($\pm$0.49); 79.9($Improved
Weight CART with ProfWeight AUC confidence profilesCART · Manufacturing wafer classification testaccuracy: 74.3% -> 87.3%Improved
Weight CART by final-layer confidence onlyCART · Manufacturing wafer classification testaccuracy: 74.3% -> 77.1%Improved
Train the simple model by distillation instead of unweighted trainingCIFAR-10 simple ResNets · CIFAR-10 holdout testaccuracy: 73.15($\pm$ 0.7) -> 65.84($\pm$0.60); 75.78($\pm$0.5) -> 70.09 ($\pm$0.19); 78.76($\pm$0.35) -> 73.4($\pm$0.64); 79.9($\Hurt
Use probe confidence AUC starting at unit 13 rather than unit 14 (ablation)ProfWeight AUC · CIFAR-10 holdout test, SM-3, SM-5, SM-7, and SM-9accuracy: 76.56 -> 75.93; 79.25 -> 78.85; 81.34 -> 81.22; 82.42 -> 82.54Mixed
Use probe confidence AUC starting at unit 15 rather than unit 14 (ablation)ProfWeight AUC · CIFAR-10 holdout test, SM-3, SM-5, SM-7, and SM-9accuracy: 76.56 -> 73.64; 79.25 -> 77.81; 81.34 -> 80.81; 82.42 -> 80.97Hurt
Weight examples with ProfWeight ReLU rather than AUC (ablation)CIFAR-10 simple ResNets · CIFAR-10 holdout testaccuracy: 77.52 vs 76.56; 78.24 vs 79.25; 80.16 vs 81.34; 81.65 vs 82.42Mixed

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