Model Selection for Off-Policy Evaluation via Pairwise Bellman Validation
stat.ML, cs.LG, econ.EM
Submitted: 2026-10-26
Updated: 2026-10-26
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