Exploration strategies for Gaussian process bandit optimization with inference regret guarantees

arXiv:2610.16187 · stat.ML, cs.LG, math.OC, stat.CO · Submitted 2026-10-12 · Read on arXiv

stat.ML, cs.LG, math.OC, stat.CO

Submitted: 2026-10-12

Updated: 2026-10-12

Code: https://github.com/hsleejw21/probabilistic-exploration

Project page: https://cma-es.github.io/cec2005

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Regret — 1× in this paper · explained in 3 episodes

Sources

• Efficient optimization of expensive black-box simulators via marginal means, with application to neutrino detector design
• Gaussian Processes and Kernel Methods: A Review on Connections and Equivalences
• Improved Regret Analysis in Gaussian Process Bandits: Optimality for Noiseless Reward, RKHS norm, and Non-Stationary Variance
• On Regret Bounds of Thompson Sampling for Bayesian Optimization
• Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency

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
• Efficient quadratic entropy with distance sketches
• Embedding-Bias in Conditional Independence Testing
• From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier