Research map / Bandits and online learning / Multi-armed bandits
From Optimality to Robustness: Adaptive Re-Sampling Strategies in Stochastic Bandits
Dorian Baudry, Patrick Saux, Odalric-Ambrym Maillard
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 |
|---|---|---|---|
| Dirichlet Sampling algorithms (BDS, QDS, RDS) vs empirical IMED and NPTS given the exact upper bound | Dirichlet Sampling · DSSAT maize planting-date 7-armed bandit | average regret | No clear effect |
| Dirichlet Sampling algorithms vs IMED and NPTS when the upper bound is conservative (1.5 times larger) | Dirichlet Sampling · DSSAT maize planting-date 7-armed bandit | average regret | Improved |
| RDS with leverage rho_n = sqrt(log(1+n)) vs other DS variants and baselines | Dirichlet Sampling · DSSAT maize planting-date 7-armed bandit | average regret | Improved |
| vary hyperparameters of Dirichlet Sampling (ablation) | Dirichlet Sampling · synthetic bandits (appendix) | regret | No clear effect |
Closest papers by meaning
- Adaptive Algorithms for Infinitely Many-Armed Bandits: A Unified Framework (JMLR 2026 · similarity 0.89)
- Recovering Bandits (NeurIPS 2019 · similarity 0.89)
- Optimal Thompson Sampling strategies for support-aware CVaR bandits (ICML 2021 · similarity 0.89)
- Adaptive Regret for Bandits Made Possible: Two Queries Suffice (ICLR 2024 · similarity 0.88)
- Best Arm Identification for Stochastic Rising Bandits (ICML 2024 · similarity 0.88)
- Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret (NeurIPS 2026 · similarity 0.88)
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.
