AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

Deep Active Learning by Leveraging Training Dynamics

Haonan Wang, Wei Huang, Ziwei Wu, Hanghang Tong, Andrew J Margenot, Jingrui He

NeurIPS 2022 · Learning theory and algorithms › Kernels and regression theory · approach: Statistical perspectives on generalization · 8 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
Increase query rounds from 1 to 10 at fixed total budget B=1000dynamicAL on CIFAR10+CNN · CIFAR10accuracy: 36.67 -> 36.84Improved
Increase query rounds from 1 to 10 at fixed total budget B=1000dynamicAL on CIFAR10+ResNet · CIFAR10accuracy: 40.09 -> 40.92Improved
Increase query rounds from 1 to 10 at fixed total budget B=1000dynamicAL on SVHN+VGG · SVHNaccuracy: 70.04 -> 76.34Improved
Increase query rounds from 1 to 10 at fixed total budget B=1000dynamicAL on Caltech101+ResNet · Caltech101accuracy: 33.82 -> 37.06Improved
Use gamma=2 in the acquisition criterion rather than the tested alternative gamma values (ablation)dynamicAL · Active learning benchmarks shown in the variant comparisontest accuracyImproved

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