Choosing automatically the right algorithm using problem descriptors is a classical component of combinatorial optimization. It is also a good tool for making evolutionary algorithms fast, robust and versatile. We present Shiwa, an algorithm good at both discrete and continuous, noisy and noise-free, sequential and parallel, black-box optimization. Our algorithm is experimentally compared to competitors on YABBOB, a BBOB comparable testbed, and on some variants of it, and then validated on several real world testbeds.
Cite
@article{arxiv.2004.14014,
title = {Versatile Black-Box Optimization},
author = {Jialin Liu and Antoine Moreau and Mike Preuss and Baptiste Roziere and Jeremy Rapin and Fabien Teytaud and Olivier Teytaud},
journal= {arXiv preprint arXiv:2004.14014},
year = {2020}
}