Research map / Learning theory and algorithms / Prediction and decision losses
Active Covering
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use greedy nearest-positive querying after an initial random sample instead of offline support estimation | Active covering · Active covering under the paper's non-parametric assumptions | excess query cost: \widetilde{\Theta}(n^{D/(D+1)}) -> \widetilde{O}(n^{(D-1)/D}) | Helped |
| Use Explore-then-Commit instead of the strongest baseline | Letters · Letters (26 label tasks) | AUC | Helped |
| Use Explore-then-Commit instead of the strongest baseline | MNIST · MNIST (10 label tasks) | AUC | Helped |
| Use Explore-then-Commit instead of the strongest baseline | Fashion MNIST · Fashion MNIST (10 label tasks) | AUC | Mixed |
| Use Explore-then-Commit instead of the strongest baseline | CIFAR10 · CIFAR10 (10 label tasks) | AUC | Mixed |
| Use Explore-then-Commit instead of the strongest baseline | SVHN · SVHN (10 label tasks) | AUC | Helped |
| Use Explore-then-Commit instead of the strongest baseline | CelebA · CelebA (40 attribute tasks) | AUC | Mixed |
| Use Explore-then-Commit rather than the offline method | Letters (label A) · Letters (label A) | AUC: 91.14 -> 97.12 | Helped |
| Use Explore-then-Commit rather than Active Isolation Forest | MNIST (label 0) · MNIST (label 0) | AUC: 90.8 -> 94.44 | Helped |
| Use Explore-then-Commit rather than Active Isolation Forest | Fashion MNIST (label 0) · Fashion MNIST (label 0) | AUC: 90.14 -> 89.75 | Hurt |
| Use Explore-then-Commit rather than Active Robust Covariance | CIFAR10 (label 0) · CIFAR10 (label 0) | AUC: 69.36 -> 70.69 | Helped |
| Use Explore-then-Commit rather than Active Robust Covariance | SVHN (label 0) · SVHN (label 0) | AUC: 39.59 -> 39.67 | No clear effect |
Closest papers by meaning
- Active Learning from Imperfect Labelers (NeurIPS 2016 · similarity 0.89)
- Active Classification with Few Queries under Misspecification (NeurIPS 2024 · similarity 0.88)
- The Power of Comparisons for Actively Learning Linear Classifiers (NeurIPS 2020 · similarity 0.88)
- Active Learning of General Halfspaces: Label Queries vs Membership Queries (NeurIPS 2024 · similarity 0.87)
- Robust Regression of General ReLUs with Queries (NeurIPS 2025 · similarity 0.85)
- A Cross-Domain Benchmark for Active Learning (NeurIPS 2024 · similarity 0.85)
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.