AI Paper Atlas

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

Training-Free Neural Active Learning with Initialization-Robustness Guarantees

Apivich Hemachandra, Zhongxiang Dai, Jasraj Singh, See-Kiong Ng, Bryan Kian Hsiang Low

ICML 2023 · Learning theory and algorithms › Prediction and decision losses · approach: Active learning and subset selection · 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
Use EV-GP to select data instead of Random, K-Means++, BADGE, or MLMOCNeural active learning · Regression taskstest MSEImproved
Use EV-GP to select data instead of the active-learning baselinesMLP neural active learning · Classification taskstest accuracyImproved
Use EV-GP data selection with convolutional architectures instead of the active-learning baselinesCNNs and WideResNets · Classification taskstest accuracyImproved
Use EV-GP to select data instead of the active-learning baselinesNeural active learning · Classification tasksoutput entropyImproved
Increase query batch size (ablation)EV-GP-Emp · Classification tasksperformanceNo clear effect
Increase query batch size (ablation)MLMOC · Classification tasksperformanceHurt
Increase query batch size (ablation)BADGE · MNISTperformanceHurt
Use a wider NN at training time (ablation)Neural active learning · Classification tasksmodel accuracyImproved
Use a wider NN at training time (ablation)Neural active learning · Classification tasksinitialization robustnessImproved
Increase NN width during data selection (ablation)EV-GP · Classification tasksmodel accuracyNo clear effect
Increase NN width during data selection (ablation)EV-GP · Classification tasksinitialization robustnessImproved
Add model selection using the EV-GP+MS criterion instead of fixing a 2-layer ReLU MLP (ablation)EV-GP · Active learning tasks where the fixed architecture is inadequatelossImproved

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