% 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:640480,
author = {Bungert, Leon and Hoffmann, Franca and Kim, Dohyeon and
Roith, Tim},
title = {{M}irror{CBO}: {A} consensus-based optimization method in
the spirit of mirror descent},
reportid = {PUBDB-2025-04802, arXiv:2501.12189},
year = {2025},
note = {66 pages, 18 figures, 19 tables},
abstract = {In this work we propose MirrorCBO, a consensus-based
optimization (CBO) method which generalizes standard CBO in
the same way that mirror descent generalizes gradient
descent. For this we apply the CBO methodology to a swarm of
dual particles and retain the primal particle positions by
applying the inverse of the mirror map, which we parametrize
as the subdifferential of a strongly convex function $ϕ$.
In this way, we combine the advantages of a derivative-free
non-convex optimization algorithm with those of mirror
descent. As a special case, the method extends CBO to
optimization problems with convex constraints. Assuming
bounds on the Bregman distance associated to $ϕ$, we
provide asymptotic convergence results for MirrorCBO with
explicit exponential rate. Another key contribution is an
exploratory numerical study of this new algorithm across
different application settings, focusing on (i)
sparsity-inducing optimization, and (ii) constrained
optimization, demonstrating the competitive performance of
MirrorCBO. We observe empirically that the method can also
be used for optimization on (non-convex) submanifolds of
Euclidean space, can be adapted to mirrored versions of
other recent CBO variants, and that it inherits from mirror
descent the capability to select desirable minimizers, like
sparse ones. We also include an overview of recent CBO
approaches for constrained optimization and compare their
performance to MirrorCBO.},
cin = {FS-CI},
cid = {I:(DE-H253)FS-CI-20230420},
pnm = {623 - Data Management and Analysis (POF4-623) / DFG project
G:(GEPRIS)544579844 - GeoMAR: Geometrische Methoden für
Adversarial Robustness (544579844)},
pid = {G:(DE-HGF)POF4-623 / G:(GEPRIS)544579844},
experiment = {EXP:(DE-MLZ)NOSPEC-20140101},
typ = {PUB:(DE-HGF)25},
eprint = {2501.12189},
howpublished = {arXiv:2501.12189},
archivePrefix = {arXiv},
SLACcitation = {$\%\%CITATION$ = $arXiv:2501.12189;\%\%$},
url = {https://bib-pubdb1.desy.de/record/640480},
}