Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Analysis and Design of Thompson Sampling for Stochastic Partial Monitoring
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 TSPM with exact posterior sampling (R=1) instead of the compared algorithms | Dynamic pricing · dp-easy and dp-hard | regret | Helped |
| Use TSPM-Gaussian (R=0) instead of BPM-TS (ablation) | Dynamic pricing · dp-easy and dp-hard | regret | Helped |
| Use a small R or zero instead of exact sampling (R=1) (ablation) | TSPM · Dynamic pricing | regret | Mixed |
| Use a small R or zero instead of exact sampling (R=1) (ablation) | TSPM · Dynamic pricing | accept-reject rejection frequency | Helped |
Closest papers by meaning
- Thompson Sampling for Stochastic Bandits with Graph Feedback (AAAI 2017 · similarity 0.90)
- On Approximate Thompson Sampling with Langevin Algorithms (ICML 2020 · similarity 0.90)
- What Does Thompson Sampling Optimize? (ICML 2026 · similarity 0.89)
- Thompson Sampling and Approximate Inference (NeurIPS 2019 · similarity 0.89)
- MOTS: Minimax Optimal Thompson Sampling (ICML 2021 · similarity 0.89)
- Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox (NeurIPS 2024 · similarity 0.88)
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.