Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Causal Bandits with Unknown Graph Structure
Yangyi Lu, Amirhossein Meisami, Ambuj Tewari
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 central-node search to identify the reward-generating variable before applying UCB | Causal bandits on directed trees · Causal trees | cumulative regret: \widetilde{O}\left(K\max\left\{\frac{1}{\Delta^2}, \frac{1}{\varepsilon^2}\right\}d(\log n)^2+\sqrt{KT}\right) versus st | Improved |
| Extend central-node search across chain components | CN-UCB · Causal forests | cumulative regret: \widetilde{O}\left(K\max\left\{\frac{1}{\Delta^2}, \frac{1}{\varepsilon^2}\right\}(d+C(D))(\log n)^2+\sqrt{KT}\right) | Improved |
| Search junction trees with central-clique interventions and restrict UCB to the identified clique | CN-UCB · General causal graphs with intersection-incomparable clique graphs | cumulative regret: \widetilde{O}\left(\left(d(\mathcal{T}_{G_R})\omega(G_R)+\sum_{G\in\text{CC}(\mathcal{E}(D))}\omega(G)\right)K\max\left\ | Improved |
Closest papers by meaning
- Partial Structure Discovery is Sufficient for No-regret Learning in Causal Bandits (NeurIPS 2024 · similarity 0.92)
- Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals (ICML 2024 · similarity 0.89)
- Linear Causal Bandits: Unknown Graph and Soft Interventions (NeurIPS 2024 · similarity 0.89)
- Efficient Contextual Bandits with Uninformed Feedback Graphs (ICML 2024 · similarity 0.87)
- Efficient Graph Bandit Learning with Side-Observations and Switching Constraints (AAAI 2025 · similarity 0.87)
- Stochastic contextual bandits with graph feedback: from independence number to MAS number (NeurIPS 2024 · 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.
