AI Paper Atlas

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

Provable Data Subset Selection For Efficient Neural Networks Training

Murad Tukan, Samson Zhou, Alaa Maalouf, Daniela Rus, Vladimir Braverman, Dan Feldman

ICML 2023 · Learning theory and algorithms › Prediction and decision losses · approach: Loss landscape analysis · 0 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 RBFNN coreset subset selection instead of GradMatchPB at 5%, 20%, and 30% budgetsResNet-18 · CIFAR10Top-1 test accuracy (%): 86.7 -> 86.9; 93.34 -> 93.61; 93.75 -> 94.44Improved
Use RBFNN coreset subset selection instead of Glister at 10% budgetResNet-18 · CIFAR10Top-1 test accuracy (%): 91.92 -> 91.4Hurt
Use RBFNN coreset subset selection instead of the strongest listed non-warm baseline at each budgetResNet-18 · CIFAR100Top-1 test accuracy (%): 41.01 -> 54.17; 60.39 -> 64.59; 70.88 -> 71.17; 72.57 -> 73.58Improved
Use RBFNN coreset subset selection instead of GradMatch at 5% budgetResNet-18 · ImageNet-2012Top-1 test accuracy (%): 47.24 -> 47.26Improved
Use RBFNN Coreset instead of GradMatchPB-WarmLeNet · MNIST, 1% and 3%Top-1 test accuracy (%): 99.0 -> 98.98; 99.23 -> 99.2Hurt
Use RBFNN Coreset instead of GradMatchPB-WarmLeNet · MNIST, 5% and 10%Top-1 test accuracy (%): 99.3 -> 99.31; 99.31 -> 99.32Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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