High-Dimensional Off-Policy Evaluation without Sample Splitting using an Onsager Correction
stat.ML, cs.LG, math.ST, stat.TH
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- Kernel Single-Index Bandits: Estimation, Inference, and Learning
- Precise gradient descent training dynamics for finite-width multi-layer neural networks
- Gradient descent inference in empirical risk minimization
- Nonparametric Bandits with Single-Index Rewards: Optimality and Adaptivity
- Cross-Fitting and Fast Remainder Rates for Semiparametric Estimation
Related papers
- Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
- Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
- Quantifying Error Propagation and Model Collapse in Diffusion Models
- Behavior of prediction performance metrics with rare events
- Statistical Inference and Learning for Shapley Additive Explanations (SHAP)
- Control Variate Design for Score-Function Gradient Estimators in Importance-Weighted Variational Inference