Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Combinatorial Causal Bandits
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 BGLM-OFU with an initialization phase and MLE confidence regions | Markovian BGLM combinatorial causal bandits · Combinatorial causal bandits, Markovian BGLM | regret: O\left(\frac{1}{\kappa} n L^{(1)}_{\max} \sqrt{DT}\log T\right) | Helped |
| Transform the hidden-variable BLM into an equivalent Markovian model and apply BGLM-OFU | BLM with hidden variables · Combinatorial causal bandits, BLM with hidden variables | regret: O\left(n\sqrt{DT}\log T\right) | Helped |
| Use linear regression instead of MLE, removing the initialization phase and its associated assumption | BLM-LR for BLM with hidden variables · Combinatorial causal bandits, BLM with hidden variables | regret: O\left(n\sqrt{DT}\log T\right) -> O\left(n^2\sqrt{DT}\log T\right) | Hurt |
Closest papers by meaning
- Combinatorial Pure Exploration of Causal Bandits (ICLR 2023 · similarity 0.94)
- Linear Causal Bandits: Unknown Graph and Soft Interventions (NeurIPS 2024 · similarity 0.90)
- Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals (ICML 2024 · similarity 0.89)
- Partial Structure Discovery is Sufficient for No-regret Learning in Causal Bandits (NeurIPS 2024 · similarity 0.89)
- Generalized Linear Bandits: Almost Optimal Regret with One-Pass Update (NeurIPS 2025 · similarity 0.88)
- Generalized Linear Bandits with Limited Adaptivity (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.