Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Adapting to misspecification in contextual bandits with offline regression oracles
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 |
|---|---|---|---|
| Add a cumulative-reward dip test and revert to the historically safe policy when the test detects misspecification | FALCON+ · Stochastic contextual bandits with misspecification | cumulative regret: The regret overhead is bounded by \mathcal{O}(\sqrt{KB}\;T) | Helped |
| Use an additional per-epoch average-reward safety test (ablation) | Safe-FALCON · Non-linearly realizable two-arm example | average per-epoch regret | Helped |
Closest papers by meaning
- Adapting to Misspecification in Contextual Bandits (NeurIPS 2020 · similarity 0.97)
- Practical Contextual Bandits with Regression Oracles (ICML 2018 · similarity 0.94)
- Active Context Selection Improves Simple Regret in Contextual Bandits (NeurIPS 2026 · similarity 0.90)
- Contextual Thompson Sampling via Generation of Missing Data (NeurIPS 2025 · similarity 0.90)
- Mixed-Effects Contextual Bandits (AAAI 2024 · similarity 0.90)
- Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback (NeurIPS 2025 · similarity 0.90)
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.