Asymptotically Log-Optimal Bayes-Assisted Confidence Sequences for Bounded Means
stat.ML, cs.LG
Submitted: 2026-05-08
Updated: 2026-11-07
Terminology
Sources
- Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models
- Closed-form empirical Bernstein confidence sequences for scalars and matrices
- Bayes-assisted Confidence Regions: Focal Point Estimator and Bounded-influence Priors
- Confidence sequences with informative, bounded-influence priors
- Prediction-Powered E-Values
- Regularized Exponentially Tilted Empirical Likelihood for Bayesian Inference
- On the near-optimality of betting confidence sets for bounded means
- Time-uniform central limit theory and asymptotic confidence sequences
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