Research map / Bandits and online learning / Contextual bandits and Thompson sampling
Optimal Regret Is Achievable with Bounded Approximate Inference Error: An Enhanced Bayesian Upper Confidence Bound Framework
Ziyi Huang, Henry Lam, Amirhossein Meisami, Haofeng Zhang
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 |
|---|---|---|---|
| use EBUCB instead of BUCB | Bernoulli bandit with misspecified posteriors (P1, P2) · 2-armed Bernoulli bandit, w=0.9/0.8/0.7 | regret | Improved |
| use EBUCB instead of Thompson sampling | Bernoulli bandit with misspecified posteriors (P1, P2) · 2-armed Bernoulli bandit, w=0.9/0.8/0.7 | regret | Improved |
| drop the horizon-dependent term (c = 0) (ablation) | EBUCB · 2-armed Bernoulli bandit | regret | No clear effect |
| increase inference error level r in worst-case posterior (ablation) | Thompson sampling · worst-case misspecified posterior | regret slope | Hurt |
| bound only one alpha-divergence of the posterior (ablation) | BUCB/EBUCB · worst-case misspecified posterior | regret | Hurt |
Closest papers by meaning
- Bayesian Regret Minimization in Offline Bandits (ICML 2024 · similarity 0.91)
- Noise-Adaptive Confidence Sets for Linear Bandits and Application to Bayesian Optimization (ICML 2024 · similarity 0.90)
- Improved Online Confidence Bounds for Multinomial Logistic Bandits (ICML 2025 · similarity 0.89)
- Adaptive Regret for Bandits Made Possible: Two Queries Suffice (ICLR 2024 · similarity 0.89)
- Only Pay for What Is Uncertain: Variance-Adaptive Thompson Sampling (ICLR 2024 · similarity 0.89)
- The Choice of Noninformative Priors for Thompson Sampling in Multiparameter Bandit Models (AAAI 2024 · similarity 0.89)
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.
