Research map / Bandits and online learning / Multi-armed bandits
Refining the Confidence Level for Optimistic Bandit Strategies
Tor Lattimore
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 ADA-UCB's refined confidence level instead of UCB's log(t) level | stochastic Gaussian bandit · Worst-case regime, equal gaps (many arms) | regret: UCB suffers about three times the regret of ADA-UCB | Improved |
| use well-tuned confidence levels as the number of arms grows | index bandit policies · Worst-case regime, equal gaps | regret | Improved |
| replace MOSS, UCB, Thompson sampling and others with ADA-UCB | 20-armed Gaussian bandit · Regret versus horizon, k = 20 | regret | Improved |
| use the log-term variant of MOSS from this paper instead of the Menard-Garivier log term (ablation) | MOSS · Gaussian bandit experiments | regret | Improved |
Closest papers by meaning
- Noise-Adaptive Confidence Sets for Linear Bandits and Application to Bayesian Optimization (ICML 2024 · similarity 0.92)
- A Closer Look at the Worst-case Behavior of Multi-armed Bandit Algorithms (NeurIPS 2021 · similarity 0.91)
- Improved Regret Analysis in Gaussian Process Bandits: Optimality for Noiseless Reward, RKHS norm, and Non-Stationary Variance (ICML 2025 · similarity 0.91)
- Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures (NeurIPS 2023 · similarity 0.91)
- Bayesian Regret Minimization in Offline Bandits (ICML 2024 · similarity 0.91)
- Gaussian Process Upper Confidence Bound Achieves Nearly-Optimal Regret in Noise-Free Gaussian Process Bandits (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.
