Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Adversarial Linear Contextual Bandits with Graph-Structured Side Observations
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 graph-structured side observations with EXP3-LGC-U instead of the edgeless-graph variant (ablation) | EXP3-LGC-U · Synthetic data, undirected feedback graph | cumulative regret | Helped |
| Use graph-structured side observations with EXP3-LGC-IX instead of the edgeless-graph variant (ablation) | EXP3-LGC-IX · Synthetic data, undirected feedback graph | cumulative regret | Helped |
| Remove explicit uniform exploration (ablation) | EXP3-LGC-U · Adversarial linear graphical contextual bandits, directed graphs | regret upper bound | Hurt |
| Use EXP3-LGC-U with graph-structured side observations rather than RobustLinEXP3 | Synthetic data · Synthetic data, undirected feedback graph | cumulative regret | Helped |
| Use EXP3-LGC-IX with graph-structured side observations rather than RobustLinEXP3 | Synthetic data · Synthetic data, undirected feedback graph | cumulative regret | Helped |
Closest papers by meaning
- An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction (NeurIPS 2025 · similarity 0.91)
- Stochastic contextual bandits with graph feedback: from independence number to MAS number (NeurIPS 2024 · similarity 0.90)
- Efficient Contextual Bandits with Uninformed Feedback Graphs (ICML 2024 · similarity 0.90)
- Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial Feedback (ICML 2025 · similarity 0.89)
- Adversarial Combinatorial Semi-bandits with Graph Feedback (ICML 2025 · similarity 0.88)
- Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback (NeurIPS 2025 · 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.