Research map / Bandits and online learning / Multi-armed bandits
The Role of Contextual Information in Best Arm Identification
Masahiro Kato, Kaito Ariu
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 contextual information in alpha-elimination (context-adjusted allocation and smaller stopping threshold) | alpha-elimination · two-armed Gaussian bandit, 1000 trials, delta=0.05 | stopping time (sample complexity) | Improved |
| use contextual information even when correlation with context is zero (allocation stays 0.5) (ablation) | alpha-elimination · two-armed Gaussian bandit, rho=0, sigma1^2=1 | stopping time | Improved |
| use Contextual Track-and-Stop instead of Track-and-Stop without context | Track-and-Stop · Bernoulli 4-arm bandit, two contexts, means 0.3/0.21/0.2/0.19 | GLRT statistic growth (sample complexity) | Mixed |
Closest papers by meaning
- Constrained Best Arm Identification (NeurIPS 2025 · similarity 0.93)
- Optimal Best-arm Identification in Linear Bandits (NeurIPS 2020 · similarity 0.92)
- Balancing Performance and Costs in Best Arm Identification (NeurIPS 2025 · similarity 0.92)
- Almost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits (NeurIPS 2024 · similarity 0.91)
- Optimal Multi-Fidelity Best-Arm Identification (NeurIPS 2024 · similarity 0.90)
- Best Arm Identification in Generalized Linear Bandits via Hybrid Feedback (NeurIPS 2026 · 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.
