Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Bayesian decision-making under misspecified priors with applications to meta-learning
Max Simchowitz, Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu, Thodoris Lykouris, Miroslav Dudík, Robert E. Schapire
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 |
|---|---|---|---|
| meta-learn the prior (MetaTS:full) instead of using a misspecified N(0,I) prior | Gaussian Thompson sampling · Gaussian MAB (6 arms, H=10) | cumulative average per-episode reward | Improved |
| also meta-learn prior covariance, not just the prior mean (ablation) | MetaTS · Gaussian MAB (6 arms, H=10) | per-episode reward | Improved |
| meta-learn the prior in Gaussian linear contextual bandit | Gaussian linear TS · Gaussian linear contextual bandit (H=20) | per-episode reward | Improved |
| use Knowledge Gradient (2-RHC) as base learner instead of Thompson sampling | Bayesian meta-learner · Discrete bandits (20 arms, 16 tasks) | per-episode reward | Improved |
Closest papers by meaning
- The Choice of Noninformative Priors for Thompson Sampling in Multiparameter Bandit Models (AAAI 2024 · similarity 0.90)
- No Regrets for Learning the Prior in Bandits (NeurIPS 2021 · similarity 0.89)
- Only Pay for What Is Uncertain: Variance-Adaptive Thompson Sampling (ICLR 2024 · similarity 0.89)
- Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown (NeurIPS 2025 · similarity 0.88)
- Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity (NeurIPS 2024 · similarity 0.88)
- Contextual Thompson Sampling via Generation of Missing Data (NeurIPS 2025 · 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.
