Research map / Bandits and online learning / Online convex optimization and games
Adaptive Selective Sampling for Online Prediction with Experts
Rui M. Castro, Fredrik Hellström, Tim van Erven
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Adapt label-query probability to weighted expert disagreement while maintaining the full-information regret guarantee | Exponentially weighted forecaster · Online prediction with expert advice | expected regret: \frac{\ln N}{\eta} + \frac{n \eta}{8} -> \frac{\ln N}{\eta} + \frac{n \eta}{8} | No clear effect |
| Use label-efficient sampling rather than collecting every label | Exponentially weighted forecaster · Threshold prediction simulation | regret | Mixed |
| Use adaptive sampling based on weighted disagreement | Exponentially weighted forecaster · Threshold prediction simulation | label complexity | Improved |
| Use adaptive sampling without knowledge of the noise parameter κ | Exponentially weighted forecaster · Threshold prediction simulation | normalized regret | Improved |
Closest papers by meaning
- Uncertainty Herding: One Active Learning Method for All Label Budgets (ICLR 2025 · similarity 0.87)
- Online Mixture of Experts: No-Regret Learning for Optimal Collective Decision-Making (NeurIPS 2025 · similarity 0.86)
- When Lower-Order Terms Dominate: Adaptive Expert Algorithms for Heavy-Tailed Losses (NeurIPS 2025 · similarity 0.86)
- Online Learning with Sublinear Best-Action Queries (NeurIPS 2024 · similarity 0.86)
- Bandit and Delayed Feedback in Online Structured Prediction (NeurIPS 2025 · similarity 0.86)
- High-Dimensional Prediction for Sequential Decision Making (ICML 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.
