Research map / Bandits and online learning / Multi-armed bandits
Learning the Best Under Constraints: A Duality-Based Framework
Mingjie Hu, Enlu Zhou, Jianqiang Hu
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 duality-based decomposition sampling (DSR) instead of uniform, best-challenger or greedy sampling rules | constrained linear BAI with covariate selection · Synthetic instance, Gaussian noise | sample complexity | Improved |
| use DSR instead of benchmark policies | constrained linear BAI · Synthetic instance, Gaussian noise | probability of correct identification | Improved |
| replace Gaussian noise with heavy-tailed t-distribution noise | DSR · Synthetic instance, 30 runs | sample complexity | No clear effect |
Closest papers by meaning
- Optimal Multi-Fidelity Best-Arm Identification (NeurIPS 2024 · similarity 0.88)
- Balancing Performance and Costs in Best Arm Identification (NeurIPS 2025 · similarity 0.87)
- Optimal Batched Best Arm Identification (NeurIPS 2024 · similarity 0.86)
- Nearly Optimal Fixed-Confidence Best-Arm Identification with 1-Bit Feedback (NeurIPS 2026 · similarity 0.86)
- Fixing the Loose Brake: Exponential-Tailed Stopping Time in Best Arm Identification (ICML 2025 · similarity 0.86)
- Optimal Top-Two Method for Best Arm Identification and Fluid Analysis (NeurIPS 2024 · similarity 0.85)
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.
