The Black Box Optimization Competition (BBComp, https://bbcomp.ini.rub.de/) has opened five new tracks consisting of challenging single- and multi-objective optimization problems. The competition is organized in the scope of the Genetic and Evolutionary Computation Conference (GECCO'2018, http://gecco-2018.sigevo.org/).

BBComp is the first competition platform in the continuous domain where test problems are truly black boxes to participants. The only information known to the optimizer and the participant is the dimension of the problem, bounds on all variables, and a budget of black box queries.

The competition is also the first web/online optimization competition in evolutionary computation domain. It aims at attacking a growing impact of over-fitting of optimization algorithms to a narrow set of existing benchmark problems. The competition was run five times so far, attracting more than 100 unique submissions, including some state-of-the-art commercial solvers.

All the material including the source code in C/C++, MATLAB, Python and Java is available at http://bbcomp.ini.rub.de . The results of the competition will be announced during GECCO'2018. Participants do not need to attend the conference or submit papers, they can even choose to be anonymous to the other participants.

Organizers:

Tobias Glasmachers, Ruhr-Universität Bochum, Germany

Ilya Loshchilov, Albert-Ludwigs-Universität Freiburg, Germany