Research map / Bandits and online learning / Multi-armed bandits
On Elimination Strategies for Bandit Fixed-Confidence Identification
Andrea Tirinzoni, Rémy Degenne
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 |
|---|---|---|---|
| add elimination stopping instead of LLR stopping (ablation) | LinGame · linear BAI | samples: 45.34 -> 43.67 | Improved |
| add elimination at sampling and stopping (ablation) | LinGame · linear BAI | samples: 45.34 -> 32.49 | Improved |
| add elimination at sampling and stopping (ablation) | FWS · linear BAI | time per iteration (ms): 0.73 -> 0.45 (-38%) | Improved |
| add elimination at sampling and stopping (ablation) | LinGapE · linear BAI | samples: 33.19 -> 29.89 | Improved |
| add elimination at sampling and stopping (ablation) | FWS · linear Top-m | time per iteration (ms): 3.0 -> 0.97 (-67%) | Improved |
| add elimination at sampling and stopping (ablation) | FWS · linear Top-m | samples: 78.28 -> 77.79 | No clear effect |
| add elimination at sampling and stopping (ablation) | MisLid · linear Top-m | samples: 87.77 -> 69.58 | Improved |
| add elimination at sampling and stopping (ablation) | LinGame · linear OSI | samples: 23.77 -> 14.87 | Improved |
| add elimination at sampling and stopping (ablation) | FWS · linear OSI | samples: 15.26 -> 14.99 | No clear effect |
| add elimination stopping only (no sampling elimination) (ablation) | FWS · linear BAI | samples: 42.26 -> 42.25 | No clear effect |
| add elimination at sampling and stopping (ablation) | Lazy TaS · linear Top-m | time per iteration (ms): 0.57 -> 0.36 (-36%) | Improved |
| full elimination instead of selective elimination (ablation) | LinGame · linear BAI | stopping time | No clear effect |
Closest papers by meaning
- Balancing Performance and Costs in Best Arm Identification (NeurIPS 2025 · similarity 0.88)
- Best Arm Identification in Generalized Linear Bandits via Hybrid Feedback (NeurIPS 2026 · similarity 0.88)
- Fixed Confidence Best Arm Identification in the Bayesian Setting (NeurIPS 2024 · similarity 0.87)
- On the Asymptotic Optimality of Confidence Interval Based Algorithms for Fixed Confidence MABs (AAAI 2025 · similarity 0.87)
- The Sampling Complexity of Condorcet Winner Identification in Dueling Bandits (NeurIPS 2026 · similarity 0.87)
- Optimal Multi-Fidelity Best-Arm Identification (NeurIPS 2024 · similarity 0.87)
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.
