UCB for Large-Scale Pure Exploration: Beyond Sub-Gaussianity

arXiv:2511.22273 · stat.ML, cs.LG · Submitted 2025-11-27 · Read on arXiv

stat.ML, cs.LG

Submitted: 2025-11-27

Updated: 2026-08-27

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• EMMA — 16× in this paper · explained in 2 episodes
• Decoupling — 7× in this paper · explained in 2 episodes
• Upper Confidence Bound — 6× in this paper
• Winter Simulation Conference — 5× in this paper
• Regret — 4× in this paper · explained in 3 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Theoretical Guarantees — 2× in this paper · explained in 2 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Monotonic Means Configuration — 1× in this paper
• Prompt Engineering — 1× in this paper · explained in 4 episodes
• Slippage Configuration — 1× in this paper

Sources

• Optimal UCB Adjustments for Large Arm Sizes
• Selecting the best system and multi-armed bandits
• On Finding the Largest Mean Among Many
• Automatic Prompt Optimization with "Gradient Descent" and Beam Search
• Sample-Efficient "Clustering and Conquer" Procedures for Parallel Large-Scale Ranking and Selection
• Achieving the Pareto Frontier of Regret Minimization and Best Arm Identification in Multi-Armed Bandits

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
• Online Conformal Prediction for Non-Exchangeable Panel Data
• Deep Time-Series Forecasting in 10 Years: A Survey