Expected Coordinate Improvement for High-Dimensional Bayesian Optimization

arXiv:2404.11917v1 Announce Type: new
Abstract: Bayesian optimization (BO) algorithm is very popular for solving low-dimensional expensive optimization problems. Extending Bayesian optimization to high dimension is a meaningful but challenging task. One of the major challenges is that it is difficult to find good infill solutions as the acquisition functions are also high-dimensional. In this work, we propose the expected coordinate improvement (ECI) criterion for high-dimensional Bayesian optimization. The proposed ECI criterion measures the potential improvement we can get by moving …

abstract acquisition algorithm arxiv bayesian challenges cs.ai cs.lg functions good improvement low major optimization popular solutions stat.ml type