Versatile Black-Box Optimization

arXiv (Cornell University)

Abstract

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.

Authors 7

1. Jialin Liu

   Southern University of Science and Technology

   Affiliation as printed

   Southern University of Science and Technology Shenzhen , China

2. Antoine Moreau

   Centre National de la Recherche Scientifique · Institut Pascal · Université Clermont Auvergne · Sigma Clermont

   Affiliation as printed

   CNRS , SIGMA Clermont , Institut Pascal Clermont-Ferrand , France

   UniversitÃľ Clermont Auvergne ,

3. Mike Preuß Aachen

   Leiden University

   Affiliation as printed

   LIACS , Universiteit Leiden , The Netherlands

4. Baptiste Rozière

   Meta (United States) · Université Paris Dauphine-PSL

   Affiliation as printed

   Facebook AI Research & Paris-Dauphine University Paris , France

5. Jérémy Rapin

   Meta (United States) · Université Paris Dauphine-PSL

   Affiliation as printed

   Facebook AI Research & Paris-Dauphine University Paris , France

6. Fabien Teytaud

   Université du littoral côte d'opale

   Affiliation as printed

   Univ. Littoral Cote d'Opale Calais , France

7. Olivier Teytaud

   Meta (United States)

   Affiliation as printed

   Facebook AI Research Paris , France