Research map / Bandits and online learning / Multi-armed bandits
Bandits with many optimal arms
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 reservoir sampling and horizon-independent UCB bonuses calibrated to the optimal-arm proportion | Sampling UCB · Cumulative regret | expected cumulative regret: O\left( \frac{\log(T) \log(1/\Delta)}{\pstar \Delta}\right) | Helped |
| Add fresh arms from the reservoir at each elimination round | Successive elimination · Best-arm identification | probability of error: 2\log(T) \exp\left(- c \frac{ \Delta^2 \pstar T}{ \log T} \right) | Helped |
| Attempt to adapt cumulative-regret performance to the optimal-arm proportion without knowing it | Cumulative-regret algorithms · Cumulative regret | expected cumulative regret: \E R(T) \geq \frac{\sqrt{T}\Delta}{4} | Hurt |
Closest papers by meaning
- Balancing Performance and Costs in Best Arm Identification (NeurIPS 2025 · similarity 0.92)
- Does 1/2-Tsallis-INF Also Work Well for Best-Arm Identification? (NeurIPS 2026 · similarity 0.92)
- Best Arm Identification for Stochastic Rising Bandits (ICML 2024 · similarity 0.92)
- Almost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits (NeurIPS 2024 · similarity 0.92)
- Near Optimal Best Arm Identification for Clustered Bandits (ICML 2025 · similarity 0.91)
- Optimal Multi-Fidelity Best-Arm Identification (NeurIPS 2024 · similarity 0.91)
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.