Research map / Bandits and online learning / Multi-armed bandits
KL-UCB-Switch: Optimal Regret Bounds for Stochastic Bandits from Both a Distribution-Dependent and a Distribution-Free Viewpoints
Aurélien Garivier, Hédi Hadiji, Pierre Ménard, Gilles Stoltz
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 switch exponent alpha=1/5 in KL-UCB-Switch instead of larger alpha (ablation) | KL-UCB-Switch · distribution-dependent regret, three bandit instances | cumulative regret | No clear effect |
| use switch exponent alpha=1/2 in KL-UCB-Switch (ablation) | KL-UCB-Switch · distribution-dependent regret, three bandit instances | cumulative regret | Mixed |
| use switch exponent alpha=8/9 in KL-UCB-Switch (ablation) | KL-UCB-Switch · distribution-dependent regret, three bandit instances | cumulative regret | Improved |
| switch from KL-UCB to KL-UCB-Switch (any of three alphas) | KL-UCB · distribution-free normalized regret R_T/sqrt(KT) | normalized regret | Improved |
| KL-UCB regret scaling with T and K versus KL-UCB-Switch | KL-UCB · distribution-free normalized regret | scaling in T and K | Hurt |
Closest papers by meaning
- Adaptation to the Range in K-Armed Bandits (JMLR 2023 · similarity 0.94)
- Stochastic Multi-armed Bandits: Optimal Trade-off among Optimality, Consistency, and Tail Risk (NeurIPS 2023 · similarity 0.92)
- Combinatorial Multi-Armed Bandit with General Reward Functions (NeurIPS 2016 · similarity 0.91)
- Bayesian Regret Minimization in Offline Bandits (ICML 2024 · similarity 0.91)
- p-Mean Regret for Stochastic Bandits (AAAI 2025 · similarity 0.91)
- Improved Regret Bounds for Linear Bandits with Heavy-Tailed Rewards (NeurIPS 2025 · similarity 0.91)
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.
