% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Georgiou:1044210,
author = {Georgiou, Anastasia and Jungen, Daniel and Kaven, Luise and
Hunstig, Verena and Frangakis, Constantine and Kevrekidis,
Ioannis and Mitsos, Alexander},
title = {{D}eterministic {G}lobal {O}ptimization of the
{A}cquisition {F}unction in {B}ayesian {O}ptimization: {T}o
{D}o or {N}ot {T}o {D}o?},
publisher = {arXiv},
reportid = {FZJ-2025-03099},
year = {2025},
abstract = {Bayesian Optimization (BO) with Gaussian Processes relies
on optimizing an acquisition function to determine sampling.
We investigate the advantages and disadvantages of using a
deterministic global solver (MAiNGO) compared to
conventional local and stochastic global solvers (L-BFGS-B
and multi-start, respectively) for the optimization of the
acquisition function. For CPU efficiency, we set a time
limit for MAiNGO, taking the best point as optimal. We
perform repeated numerical experiments, initially using the
Muller-Brown potential as a benchmark function, utilizing
the lower confidence bound acquisition function; we further
validate our findings with three alternative benchmark
functions. Statistical analysis reveals that when the
acquisition function is more exploitative (as opposed to
exploratory), BO with MAiNGO converges in fewer iterations
than with the local solvers. However, when the dataset lacks
diversity, or when the acquisition function is overly
exploitative, BO with MAiNGO, compared to the local solvers,
is more likely to converge to a local rather than a global
ly near-optimal solution of the black-box function. L-BFGS-B
and multi-start mitigate this risk in BO by introducing
stochasticity in the selection of the next sampling point,
which enhances the exploration of uncharted regions in the
search space and reduces dependence on acquisition function
hyperparameters. Ultimately, suboptimal optimization of
poorly chosen acquisition functions may be preferable to
their optimal solution. When the acquisition function is
more exploratory, BO with MAiNGO, multi-start, and L-BFGS-B
achieve comparable probabilities of convergence to a
globally near-optimal solution (although BO with MAiNGO may
require more iterations to converge under these
conditions).},
keywords = {Optimization and Control (math.OC) (Other) / Machine
Learning (cs.LG) (Other) / FOS: Mathematics (Other) / FOS:
Computer and information sciences (Other)},
cin = {ICE-1},
cid = {I:(DE-Juel1)ICE-1-20170217},
pnm = {899 - ohne Topic (POF4-899)},
pid = {G:(DE-HGF)POF4-899},
typ = {PUB:(DE-HGF)25},
doi = {10.48550/ARXIV.2503.03625},
url = {https://juser.fz-juelich.de/record/1044210},
}