The Behavior and Convergence of Local Bayesian Optimization

arXiv:2305.15572v3 Announce Type: replace
Abstract: A recent development in Bayesian optimization is the use of local optimization strategies, which can deliver strong empirical performance on high-dimensional problems compared to traditional global strategies. The "folk wisdom" in the literature is that the focus on local optimization sidesteps the curse of dimensionality; however, little is known concretely about the expected behavior or convergence of Bayesian local optimization routines. We first study the behavior of the local approach, and find that the statistics …

abstract arxiv bayesian behavior convergence cs.lg development dimensionality focus global however literature optimization performance stat.ml strategies the curse of dimensionality type