% 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{Bungert:607321,
author = {Bungert, Leon and Roith, Tim and Wacker, Philipp},
title = {{P}olarized consensus-based dynamics for optimization and
sampling},
journal = {Mathematical programming},
volume = {21},
issn = {0025-5610},
address = {Heidelberg},
publisher = {Springer},
reportid = {PUBDB-2024-01832},
pages = {125 - 155},
year = {2024},
note = {L:MB},
abstract = {In this paper we propose polarized consensus-based dynamics
in order to make consensus-based optimization (CBO) and
sampling (CBS) applicable for objective functions with
several global minima or distributions with many modes,
respectively. For this, we ``polarize'' the dynamics with a
localizing kernel and the resulting model can be viewed as a
bounded confidence model for opinion formation in the
presence of common objective. Instead of being attracted to
a common weighted mean as in the original consensus-based
methods, which prevents the detection of more than one
minimum or mode, in our method every particle is attracted
to a weighted mean which gives more weight to nearby
particles. We prove that in the mean-field regime the
polarized CBS dynamics are unbiased for Gaussian targets. We
also prove that in the zero temperature limit and for
sufficiently well-behaved strongly convex objectives the
solution of the Fokker--Planck equation converges in the
Wasserstein-2 distance to a Dirac measure at the minimizer.
Finally, we propose a computationally more efficient
generalization which works with a predefined number of
clusters and improves upon our polarized baseline method for
high-dimensional optimization.},
cin = {FS-CI},
ddc = {510},
cid = {I:(DE-H253)FS-CI-20230420},
pnm = {623 - Data Management and Analysis (POF4-623) / DFG project
G:(GEPRIS)390685689 - EXC 2046: MATH+: Berlin Mathematics
Research Center (390685689) / 05M20WEA - Verbundprojekt
05M2020 - DELETO: Maschinelles Lernen bei korrelativer MR
und Hochdurchsatz-NanoCT. Teilvorhaben 3: Gelernte
Regularisierungsmethoden und lernbasierte Verfahren für
korrelatives MR. (BMBF-05M20WEA) / NoMADS - Nonlocal Methods
for Arbitrary Data Sources (777826)},
pid = {G:(DE-HGF)POF4-623 / G:(GEPRIS)390685689 /
G:(DE-Ds200)BMBF-05M20WEA / G:(EU-Grant)777826},
experiment = {EXP:(DE-MLZ)NOSPEC-20140101},
typ = {PUB:(DE-HGF)16},
eprint = {2211.05238},
howpublished = {arXiv:2211.05238},
archivePrefix = {arXiv},
SLACcitation = {$\%\%CITATION$ = $arXiv:2211.05238;\%\%$},
UT = {WOS:001236090900001},
doi = {10.1007/s10107-024-02095-y},
url = {https://bib-pubdb1.desy.de/record/607321},
}