Kernel-based guarantees for nonlinear parametric models in Bayesian optimization
stat.ML, cs.LG
Submitted: 2026-05-13
Updated: 2026-11-17
Project page: https://realworldml.github.io/files/cr/paper64.pdf
Terminology
Sources
- A Gaussian Process View on Observation Noise and Initialization in Wide Neural Networks
- Sample-Then-Optimize Batch Neural Thompson Sampling
- Neural Tangent Kernel: Convergence and Generalization in Neural Networks
- Gaussian Processes and Kernel Methods: A Review on Connections and Equivalences
- A Study of Bayesian Neural Network Surrogates for Bayesian Optimization
- Vector-valued self-normalized concentration inequalities beyond sub-Gaussianity
- Batch Bayesian optimisation via density-ratio estimation with guarantees
- Modern Bayesian Experimental Design
- Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design
- Variational Search Distributions
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