Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Bandit Quickest Changepoint Detection
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 adaptive epsilon-GCD instead of uniform random sampling | epsilon-GCD · Line graph N=25, pointy A1 | stopping time: 764 ± 194 -> 253 ± 216 | Helped |
| use adaptive epsilon-GCD instead of uniform random sampling | epsilon-GCD · Line graph N=10, pointy A1 | stopping time: 306 ± 76 -> 112 ± 74 | Helped |
| reuse exploitation-round data for parameter estimation (epsilon-GCD+) (ablation) | epsilon-GCD · Line graph N=25, pointy A1 | stopping time: 253 ± 216 -> 191 ± 154 | Helped |
| give the algorithm knowledge of pre- and post-change distributions (Oracle) | epsilon-GCD · Line graph N=25, pointy A1 | stopping time: 253 ± 216 -> 31 ± 5 | Helped |
| increase graph size from 10 to 25 | epsilon-GCD · Line graph, pointy A1 | stopping time: 112 ± 74 -> 253 ± 216 | Hurt |
| increase graph size from 10 to 25 | Oracle · Line graph, pointy A1 | stopping time: 30 ± 5 -> 31 ± 5 | No clear effect |
| vary changepoint location nu | all methods · Line graph synthetic | average expected delay | No clear effect |
Closest papers by meaning
- Fixed-Confidence Multiple Change Point Identification under Bandit Feedback (ICML 2025 · similarity 0.86)
- The Sample Complexity of Multiple Change Point Identification under Bandit Feedback (NeurIPS 2026 · similarity 0.86)
- Reducing sequential change detection to sequential estimation (ICML 2024 · similarity 0.85)
- Non-Stationary Lipschitz Bandits (NeurIPS 2025 · similarity 0.83)
- Instance-Dependent Regret Bounds for Nonstochastic Linear Partial Monitoring (NeurIPS 2025 · similarity 0.83)
- Non-stationary Bandit Convex Optimization: A Comprehensive Study (NeurIPS 2025 · similarity 0.83)
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.