On Evolutionary Algorithms for Industrial Optimization

Abstract

Many of the industrially motivated optimization problems that I have dealt with in my career are characterized by the fact that only a small number of function evaluations can be afforded. However, in Evolutionary Computation most fundamental and empirical research focuses on large evaluation budgets, such that there is a lack of algorithm variants for this application domain.

In this presentation, I will discuss a few insights resulting from a low-budget algorithm comparison on BBOB, performed with some variants of evolution strategies. As a competing approach, I will also introduce variants of efficient global optimization, which combine data driven learning and direct optimization. In this domain, I will present an extension to mixed-integer categorical search spaces and potential applications (e.g., in ship design and convolutional neural network configuration). This new algorithm includes an evolution strategy as an optimizer for the so-called infill criterion (acquisition function).

The talk concludes by providing a short overview of topics and industrial projects in my research group.

Thomas Bäck (Bild: Thomas Bäck)

CV

Thomas Bäck is professor of Computer Science at the Leiden Institute of Advanced Computer Science, Leiden University, Netherlands, since 2002.

He received his PhD in Computer Science from Dortmund University, Germany, in 1994, and was leader of the Center for Applied Systems Analysis at the Informatik Centrum Dortmund until 2000.

Until 2007, Thomas was also CTO of NuTech Solutions, Inc. (Charlotte, NC), where he gained ample experience in solving real-world problems in optimization and data analytics, by working with global enterprises in the automotive and other industry sectors.

Thomas received the IEEE Computational Intelligence Society (CIS) Evolutionary Computation Pioneer Award for his contributions in synthesizing evolutionary computation (2015), was elected as a fellow of the International Society of Genetic and Evolutionary Computation (ISGEC) for fundamental contributions to the field (2003), and received the best dissertation award from the "Gesellschaft für Informatik" in 1995.

Thomas has more than 300 publications, as well as two books on evolutionary algorithms: Evolutionary Algorithms in Theory and Practice (1996), Contemporary Evolution Strategies (2013). He is co-editor of the Handbook of Evolutionary Computation and the Handbook of Natural Computing. Thomas is also Co-Editor-in-Chief of the Natural Computing Series (Springer) and the journal Theoretical Computer Science C (Elsevier), and editorial board member of various journals.

Thomas’ research interests are in foundations and applications of evolutionary computation, efficient global optimization, and multiple objective optimization. His recent research also addresses optimization methods in machine learning, e.g., for hyperparameter optimization, as well as supervised and unsupervised machine learning for smart industry applications.