Research map / Bandits and online learning / Multi-armed bandits
An Optimal Elimination Algorithm for Learning a Best Arm
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 aggressive elimination before the final selection stage | Approximate Best Arm (ABA) · Worst-case PAC best-arm, n → ∞ and δ → 0 | sample complexity: (2+\lambda)\frac{n}{\epsilon^2}\log \frac{1}{\delta} | Helped |
| Allocate different estimation accuracies to the best arm and the other arms | Approximate Best Arm Likelihood Estimation by Hoeffding (Abaleh) · Worst-case PAC best-arm, n > 1/δ and δ < δ₀ | sample complexity: (1+\lambda)\frac{n}{2\epsilon^2}\log \frac{1}{\delta} | Helped |
| Use aggressive elimination under the unique ε-best-arm assumption | Simple Approximate Best Arm (SABA) · Worst-case PAC best-arm, δ ≤ 0.05 and n ≥ max{1/δ⁴, 10⁵} | sample complexity: \frac{4n}{\epsilon^2}\log \frac{1}{\delta} | Helped |
Closest papers by meaning
- Optimal Batched Best Arm Identification (NeurIPS 2024 · similarity 0.88)
- Optimal Multi-Fidelity Best-Arm Identification (NeurIPS 2024 · similarity 0.88)
- Fixed Confidence Best Arm Identification in the Bayesian Setting (NeurIPS 2024 · similarity 0.87)
- Balancing Performance and Costs in Best Arm Identification (NeurIPS 2025 · similarity 0.87)
- Breaking the $\log(1/\Delta_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids (ICLR 2025 · similarity 0.86)
- Near Optimal Best Arm Identification for Clustered Bandits (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.