Prequential E-Values for Selected-GP Near-Optimality Certificates
cs.LG
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/atavory/gp_evalue
Sources
- No-Regret Bayesian Optimization with Unknown Hyperparameters
- On Kernelized Multi-armed Bandits
- Game-theoretic statistics and safe anytime-valid inference
- Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design
- E-values: Calibration, combination, and applications
- Regret-Based $(\epsilon,\delta)$-optimal Stopping Criteria for Bayesian Optimization
- Stopping Bayesian Optimization with Probabilistic Regret Bounds
- Post-selection inference for e-value based confidence intervals
- Winners with Confidence: Discrete Argmin Inference with an Application to Model Selection
- A Flexible Defense Against the Winner's Curse
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