AI RESEARCH
Goal-Oriented Lower-Tail Calibration of Gaussian Processes for Bayesian Optimization
arXiv CS.LG
•
ArXi:2605.20145v1 Announce Type: cross Bayesian optimization (BO) selects evaluation points for expensive black-box objectives using Gaussian process (GP) predictive distributions. Kernel choice and hyperparameter selection can lead to miscalibrated predictive distributions and an inappropriate exploration-exploitation trade-off. For minimization, sampling criteria such as expected improvement (EI) depend on the predictive distribution below the current best value, so lower-tail miscalibration directly affects the sampling decision.