Sampling Allocation of LinUCB: Optimal Design Limits in the Small-Gap Regime

cs.LG, stat.ML

Submitted: 2026-10-05

Updated: 2026-10-05

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

Sources

• The Typical Behavior of Bandit Algorithms
• Diffusion Approximations for Thompson Sampling in the Small Gap Regime
• Statistical Inference under Adaptive Sampling with LinUCB
• Stable Thompson Sampling: Valid Inference via Variance Inflation
• Thompson sampling: Precise arm-pull dynamics and adaptive inference
• Inference with the Upper Confidence Bound Algorithm
• A Diffusion Analysis of Policy Gradient for Stochastic Bandits

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks