Research map / Learning theory and algorithms / Sample complexity
Active Learning from Imperfect Labelers
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 abstention responses to guide binary search (adaptive test on abstention counts) instead of only 0/1 labels | threshold learning with abstaining labeler · 1D thresholds, Condition 3 (abstention-only, monotone abstention) | query complexity: removes the 1/eps^{2beta} factor, giving O~(1/f(eps/2)) instead of O~(1/f(eps/2) eps^{-2beta}) | Helped |
| Abstention-based test (CheckSignificant-Var) replaces 0/1-label test when abstention is strictly monotone | threshold search · 1D thresholds | query complexity | Helped |
| Plateau abstention rate near boundary (violating monotonicity condition) instead of strictly increasing | threshold search · 1D thresholds, P(abstain)=0.68 on [0.2,0.4] | query complexity | Hurt |
| Lower bound for abstention-only vs noise-only labelers of equal corruption | threshold learning · theoretical comparison | query complexity exponent: abstention-only O~(eps^-gamma) vs noise-only O~(eps^-2gamma) | Helped |
Closest papers by meaning
- Active Classification with Few Queries under Misspecification (NeurIPS 2024 · similarity 0.88)
- Active Learning From Positive and Unlabeled Examples (NeurIPS 2026 · similarity 0.88)
- Uncertainty Herding: One Active Learning Method for All Label Budgets (ICLR 2025 · similarity 0.86)
- Active Learning of General Halfspaces: Label Queries vs Membership Queries (NeurIPS 2024 · similarity 0.86)
- Querying Easily Flip-flopped Samples for Deep Active Learning (ICLR 2024 · similarity 0.86)
- Robust Regression of General ReLUs with Queries (NeurIPS 2025 · similarity 0.86)
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.