AI Paper Atlas

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

Making Look-Ahead Active Learning Strategies Feasible with Neural Tangent Kernels

Mohamad Amin Mohamadi, Wonho Bae, Danica J. Sutherland

NeurIPS 2022 · Learning theory and algorithms › Prediction and decision losses · approach: Active learning and subset selection · 6 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 empirical-NTK MLMOC look-ahead acquisition instead of random acquisitionNeural-network active learning · SVHN, CIFAR10, and CIFAR100accuracyImproved
Use empirical-NTK MLMOC instead of existing look-ahead strategiesNeural-network active learning · MNISTaccuracyImproved
Use sequential querying with each new true label incorporated before the next queryNTK active learning · MNISTaccuracyImproved
Approximate look-ahead retraining with empirical NTK rather than naively retraining with SGD for each candidateMLMOC · MNISTquery runtime: more than 100 times fasterImproved
Use empirical NTK rather than infinite NTK (ablation)NTK look-ahead active learning · MNISTaccuracyImproved
Use empirical-NTK block computation (ablation)NTK MLMOC · MNISTquery runtimeImproved
Use the most likely pseudo-label rather than averaging over hypothetical labels (ablation)MLMOC · Active learningaccuracyNo clear effect
Vary the maximum width of the WideResNet (ablation)NTK active learning · MNISTaccuracyNo clear effect
Train with L2 loss instead of cross-entropy (ablation)Random and NTK acquisition · MNISTaccuracyNo clear effect

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