Research map / Bandits and online learning / Multi-armed bandits
Best Arm Identification with Fixed Budget: A Large Deviation Perspective
Po-An Wang, Ruo-Chun Tzeng, Alexandre Proutiere
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 |
|---|---|---|---|
| Use aggressive rather than conservative continuous elimination | Continuous Rejects · 55-arm convex mapping, T=3,000 | error probability (%): 7.1 -> 4.7 | Improved |
| Use aggressive rather than conservative continuous elimination | Continuous Rejects · 55-arm convex mapping, T=4,000 | error probability (%): 2.6 -> 1.6 | Improved |
| Use aggressive rather than conservative continuous elimination | Continuous Rejects · 55-arm convex mapping, T=5,000 | error probability (%): 1.1 -> 0.6 | Improved |
| Use conservative continuous elimination instead of Successive Rejects | Best-arm identification · 55-arm convex mapping, T=3,000 | error probability (%): 5.5 -> 7.1 | Hurt |
| Use conservative continuous elimination instead of Successive Rejects | Best-arm identification · 55-arm convex mapping, T=4,000 | error probability (%): 2.8 -> 2.6 | Improved |
| Use conservative continuous elimination instead of Successive Rejects | Best-arm identification · 55-arm convex mapping, T=5,000 | error probability (%): 1.3 -> 1.1 | Improved |
| Use aggressive continuous elimination instead of Successive Rejects | Best-arm identification · 55-arm convex mapping, T=3,000 | error probability (%): 5.5 -> 4.7 | Improved |
| Use aggressive continuous elimination instead of Successive Rejects | Best-arm identification · 55-arm convex mapping, T=4,000 | error probability (%): 2.8 -> 1.6 | Improved |
| Use aggressive continuous elimination instead of Successive Rejects | Best-arm identification · 55-arm convex mapping, T=5,000 | error probability (%): 1.3 -> 0.6 | Improved |
Closest papers by meaning
- Balancing Performance and Costs in Best Arm Identification (NeurIPS 2025 · similarity 0.92)
- On the Asymptotic Optimality of Confidence Interval Based Algorithms for Fixed Confidence MABs (AAAI 2025 · similarity 0.91)
- Optimal Multi-Fidelity Best-Arm Identification (NeurIPS 2024 · similarity 0.91)
- On Universally Optimal Algorithms for A/B Testing (ICML 2024 · similarity 0.91)
- Best Arm Identification for Stochastic Rising Bandits (ICML 2024 · similarity 0.91)
- Breaking the $\log(1/\Delta_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids (ICLR 2025 · similarity 0.90)
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.
