Statistical Inference for Misspecified Contextual Bandits
Yongyi Guo, Ziping Xu
stat.ML, cs.LG
Submitted: 2026-06-21
Comments: arXiv admin note: substantial text overlap with arXiv:2509.06287
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Estimation Considerations in Contextual Bandits
- Contextual Bandits in a Survey Experiment on Charitable Giving: Within-Experiment Outcomes versus Policy Learning
- Semi-parametric inference based on adaptively collected data
- Statistical Inference After Adaptive Sampling for Longitudinal Data
- Replicable Bandits for Digital Health Interventions
- Inference with the Upper Confidence Bound Algorithm
- Stable Thompson Sampling: Valid Inference via Variance Inflation
- Near-optimal inference in adaptive linear regression
- UCB algorithms for multi-armed bandits: Precise regret and adaptive inference
- Adaptive Off-Policy Inference for M-Estimators Under Model Misspecification
- A Unified Switching System Perspective and O.D.E. Analysis of Q-Learning Algorithms
- User-friendly tail bounds for sums of random matrices
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
- Scalable Posterior Uncertainty for Flexible Density-Based Clustering
- A Transport Geometry of Benign Overfitting
- Efficient quadratic entropy with distance sketches