Research map / Label-efficient and robust learning / Semi-supervised learning
The Power of Comparisons for Actively Learning Linear Classifiers
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 |
|---|---|---|---|
| Combine active pool-based learning with comparison queries | PAC learning of linear separators · Log-concave distributions | query complexity: \Omega_d\left(\left(\frac{1}{\varepsilon}\right)^{\frac{d-1}{d+1}}\right) -> \tilde{O}\left(\left(d+\log\left(\frac{1}{\ | Helped |
| Use active label queries without comparisons | PAC learning of linear separators · Uniform unit ball | query complexity: \Omega_d\left(\left(\frac{1}{\varepsilon}\right)^{\frac{d-1}{d+1}}\right) | No clear effect |
| Use comparisons without active querying | PAC learning of linear separators · Uniform unit ball | sample complexity: \Omega \left( \frac{1}{\varepsilon} \right) | No clear effect |
| Add comparison queries to passive RPU learning | RPU learning of linear separators · Uniform unit ball | sample complexity: \tilde{\Theta}_d\left( \left (\frac{1}{\varepsilon} \right )^{\frac{d+1}{2}} \right) -> \tilde{O}\left(\frac{d}{\varepsi | Helped |
| Add comparison queries to active pool-based RPU learning | RPU learning of linear separators · Uniform unit ball | query complexity: \tilde{\Omega}_d\left(\left(\frac{1}{\varepsilon}\right)^{\frac{d-1}{2}}\right) -> \tilde{O}\left(d\log^2\left(\frac{1}{ | Helped |
Closest papers by meaning
- Active Learning from Imperfect Labelers (NeurIPS 2016 · similarity 0.89)
- Cost-Accuracy Aware Adaptive Labeling for Active Learning (AAAI 2020 · similarity 0.89)
- Re-Active Learning: Active Learning with Relabeling (AAAI 2016 · similarity 0.89)
- Active Learning From Positive and Unlabeled Examples (NeurIPS 2026 · similarity 0.87)
- Instance-wise Supervision-level Optimization in Active Learning (CVPR 2025 · similarity 0.87)
- A Cross-Domain Benchmark for Active Learning (NeurIPS 2024 · similarity 0.87)
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.