Research map / Bandits and online learning / Contextual bandits and Thompson sampling
No Regrets for Learning the Prior in Bandits
Soumya Basu, Branislav Kveton, Manzil Zaheer, Csaba Szepesvari
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 |
|---|---|---|---|
| Marginalize uncertainty over the meta-parameter instead of sampling a meta-parameter at the start of each task | Thompson sampling for sequential bandit tasks · Gaussian bandit, σq = 0.5 | cumulative regret: about 30% lower | Improved |
| Marginalize uncertainty over the meta-parameter instead of sampling a meta-parameter at the start of each task | Thompson sampling for sequential bandit tasks · Gaussian bandit, σq = 1 | cumulative regret | Improved |
| Marginalize uncertainty over the meta-parameter instead of sampling a meta-parameter at the start of each task | Thompson sampling for sequential bandit tasks · Linear bandit, σq = 1 | cumulative regret: more than three times lower regret | Improved |
Closest papers by meaning
- The Choice of Noninformative Priors for Thompson Sampling in Multiparameter Bandit Models (AAAI 2024 · similarity 0.91)
- Only Pay for What Is Uncertain: Variance-Adaptive Thompson Sampling (ICLR 2024 · similarity 0.91)
- Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown (NeurIPS 2025 · similarity 0.90)
- Improved Bayes Regret Bounds for Multi-Task Hierarchical Bayesian Bandit Algorithms (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 0.90)
- Adaptive Regret for Bandits Made Possible: Two Queries Suffice (ICLR 2024 · 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.
