Research map / Bandits and online learning / Multi-armed bandits
Quantile Bandits for Best Arms Identification
Mengyan Zhang, Cheng Soon Ong
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 |
|---|---|---|---|
| Q-SAR instead of Q-SR for multiple best arms (m=5) | Q-SAR · Environment I and II, m=5 | probability of error | Improved |
| Q-SAR instead of Q-SR for single best arm (m=1) | Q-SAR · Environment I and II, m=1 | probability of error | No clear effect |
| Q-SAR instead of Q-Uniform and Q-BE baselines | Q-SAR · Environment I (0.5-quantile) | probability of error | Improved |
| 0.8-quantile based Q-SAR/Q-SR instead of mean-based SAR/SR | Q-SAR · Environment II | probability of error | Improved |
| Q-SAR instead of Q-SR at small sample size | Q-SAR · Environment II | probability of error | Improved |
| Use 0.8-quantile instead of mean as arm summary (larger min gap) | Q-SAR · Environment II | probability of error: 0.40 -> 1.21 | Improved |
| Q-SAR on vaccine simulation, m=3 | Q-SAR · Vaccine 0.5-quantile | probability of error | Improved |
| Q-SAR on vaccine simulation with outliers, m=1 | Q-SAR · Vaccine 0.5-quantile | probability of error | No clear effect |
| Lower quantile level tau | Q-SAR bound · problem complexity H_tau | probability of error | Improved |
Closest papers by meaning
- Bandits with many optimal arms (NeurIPS 2021 · similarity 0.91)
- Optimal Best-arm Identification in Linear Bandits (NeurIPS 2020 · similarity 0.90)
- Minimax Optimal Fixed-Budget Best Arm Identification in Linear Bandits (NeurIPS 2022 · similarity 0.90)
- Does 1/2-Tsallis-INF Also Work Well for Best-Arm Identification? (NeurIPS 2026 · similarity 0.89)
- Balancing Performance and Costs in Best Arm Identification (NeurIPS 2025 · similarity 0.88)
- Almost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits (NeurIPS 2024 · similarity 0.88)
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.
