Research map / Learning theory and algorithms / Sample complexity
ActiveHedge: Hedge meets Active Learning
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 ActiveHedge (active label queries with burn-in phase) instead of querying every label as in Hedge | prediction with expert advice, linear and threshold experts · Synthetic experiments (M=10000, N=100) | label queries and regret vs Hedge | No clear effect |
| Use ActiveHedge instead of Cesa-Bianchi et al. (2005) selective sampling | prediction with expert advice on high-compactness identity-like experts · Synthetic identity experts (zeta = O(N)) | regret and labels queried | Helped |
Closest papers by meaning
- Transductive Active Learning: Theory and Applications (NeurIPS 2024 · similarity 0.88)
- Active Learning of General Halfspaces: Label Queries vs Membership Queries (NeurIPS 2024 · similarity 0.87)
- On the Universal Near Optimality of Hedge in Combinatorial Settings (NeurIPS 2025 · similarity 0.87)
- Universal Rates for Active Learning (NeurIPS 2024 · similarity 0.86)
- Active Classification with Few Queries under Misspecification (NeurIPS 2024 · similarity 0.86)
- Uncertainty Herding: One Active Learning Method for All Label Budgets (ICLR 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.