Research map / Bandits and online learning / Multi-armed bandits
Combinatorial Pure Exploration with Full-Bandit or Partial Linear Feedback
Yihan Du, Yuko Kuroki, Wei Chen
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 PolyALBA instead of ALBA or RAGE for CPE-BL matching instances | CPE-BL on matchings · 3-by-3 to 5-by-5 matching instances | running time | Improved |
| Use PolyALBA instead of ALBA or RAGE for CPE-BL matching instances | CPE-BL on matchings · 3-by-3 to 5-by-5 matching instances | sample complexity | Hurt |
| Use GCB-PE for nonlinear reward identification | CPE-PL · Matching instances with nonlinear reward | answer correctness | Improved |
| Use GCB-PE instead of ALBA or RAGE | CPE-PL · Matching instances with nonlinear reward | running time | Improved |
| Restrict the G-optimal sampling distribution to a polynomial-size support | PolyALBA · CPE-BL | computational efficiency | Improved |
| Use a non-uniform allocation over the global observer set instead of uniform sampling | GCB-PE · CPE-PL | sample complexity | Improved |
Closest papers by meaning
- Thompson Sampling for Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit (AAAI 2024 · similarity 0.90)
- Optimal and Efficient Contextual Combinatorial Semi-bandits with General Function Approximation (NeurIPS 2026 · similarity 0.89)
- Infrequent Exploration in Linear Bandits (NeurIPS 2025 · similarity 0.88)
- Adversarial Combinatorial Semi-bandits with Graph Feedback (ICML 2025 · similarity 0.87)
- Oracle-Efficient Combinatorial Semi-Bandits (NeurIPS 2025 · similarity 0.87)
- FraPPE: Fast and Efficient Preference-Based Pure Exploration (NeurIPS 2025 · 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.
