Evolutionary Computation in Practice at ACM GECCO

July 16, 2025

The ACM Genetic and Evolutionary Computation Conference (GECCO) presents the latest high-quality results in genetic and evolutionary computation since 1999. Topics include: genetic algorithms, genetic programming, swarm intelligence, complex systems, evolutionary combinatorial optimization and metaheuristics, evolutionary machine learning, learning for evolutionary computation, evolutionary multiobjective optimization, evolutionary numerical optimization, neuroevolution, real world applications, search-based software engineering, theory, benchmarking, reproducibility, hybrids and more.

In the Evolutionary Computation in Practice (ECiP) track, well-known speakers with outstanding reputation in academia and industry present background and insider information on how to establish reliable cooperation with industrial partners. They actually run companies or are involved in cooperation between academia and industry. 
If you attend, you will learn multiple ways to extend EC practice beyond the approaches found in textbooks. Experts in real-world optimization with decades of experience share their approaches to creating successful projects for real-world clients. Some of what they do is based on sound project management principles, and some is specific to our type of optimization projects. If you are working in academia and are interested in managing industrial projects, you will receive valuable hints for your own research projects.

The “Evolutionary Computation in Practice” Track will be organized by Richard Schulz and Prof. Dr. Thomas Bartz-Beielstein.

ECiP @GECCOConf 2025

In 2025, ECiP will be an in-person event. We will do our best to enable opportunities for establishing contacts among participants.

Program (Overview)

Time: 12:00 – 13:30 (UTC+2)
Date: July, 16th 2025

SessionSpeakerTitleAffiliation
S-1Dr. Roman KalkreuthOn the antagonism between foundations and applications in graph-based genetic programmingRWTH Aachen
S-2Dr. Farha Anjum KhanRobust Contextual Preferential Bayesian Optimization for Real-World Applications with Biased Data and Minimal Expert InvolvemenContinental-Corporation
S-3Dr. Xavier Bonet-MonroigQuantum (computing) needs you! Quantum (computing) wants you!Honda Research Institute Europe

Abstracts and Bios

S-1: On the antagonism between foundations and applications in graph-based genetic programming

Abstract:
Various advanced methods for genetic variation have been proposed for graph-based genetic programming in recent years that can significantly enhance the search performance. However, these methods have not achieved any practical relevance yet. In the meantime, however, a relatively simple 1+lambda search strategy, originally proposed as the base algorithm for the graph-based genetic programming variant cartesian genetic programming, has been successfully applied to various real-world problems. A quite contrasting development that gives certainly cause for reflection on the antagonism between foundations and applications in this field.

Bio:
Roman Kalkreuth is currently an assistant professor at RWTH Aachen University in Germany. Primarily, his research focuses on the analysis and development of algorithms for graph-based genetic programming. From 2015 until 2022, he was a research associate of the Computational Intelligence Research Group of Professor Guenter Rudolph at TU Dortmund University (Germany). Roman Kalkreuth defended his PhD thesis in July 2021 and then took up a postdoctoral researcher position within Professor Rudolph’s group. From October 2022 to June 2023, he worked in the Natural Computing Research Group of Professor Dr. Thomas Bäck at the Leiden Institute of Advanced Computer Science, which is part of Leiden University. He joined Laboratoire d’Informatique de Paris 6 (LIP6) of Sorbonne University in Paris as a postdoctoral researcher under supervision of Carola Doerr from June 2023 until March 2024. He then took up an assistant professor position at RWTH Aachen University, which started in April 2024.

S-2: Robust Contextual Preferential Bayesian Optimization for Real-World Applications with Biased Data and Minimal Expert Involvement

Abstract:
Solving real-world optimization problems is often hindered by unknown objectives and biased data. While Preferential Bayesian Optimization (PBO) offers a promising framework, existing approaches typically rely on predefined utility functions, interactive learning, or full Pareto front estimation; each demanding costly expert involvement.
We propose a novel offline method to learn interpretable utility functions using expert knowledge and historical data. By incorporating coarse prior information about the utility space and modeling uncertainty through a full Bayesian posterior, our approach reduces sample complexity and propagates uncertainty throughout the optimization process.
Evaluated across four domains, our method consistently outperforms standard Gaussian Process models and Bayesian Optimization with Preference Exploration (BOPE), even under biased sampling: achieving robust, high-quality results without repeated expert input.

Bio:
Dr. Farha Anjum Khan is a researcher working at the intersection of Interactive Machine Learning and Human-Centered AI, with a background in physics. Her work explores how human feedback can guide machine learning systems, particularly through preferential Bayesian Optimization. She applies these methods in domains such as automotive systems, adaptive interfaces, and sensor-driven environments. Farha is especially interested in building AI systems that are not only effective but also transparent, inclusive, and grounded in real-world impact.

S-3: Quantum (computing) needs you! Quantum (computing) wants you!

Abstract:
In this talk I will try to convince you that the quantum computing community is in urgent need for your help, the evolutionary and optimization community. I will start with a basic introduction of quantum computation, with special attention to what makes them strictly more powerful than classical computers (with caveats). Next, I will show how poorly classical optimization algorithms have been used in the field, and our attempt at solving this issue. Then, I will present several parts of the quantum computing pipeline where evolutionary optimization can be of assistance. I will finish the talk with a cry for help, in an attempt to make everyone in the evolutionary computation and optimization community interested in the hard problems we are facing with quantum computers.

Bio:
Xavier Bonet-Monroig is a Senior Scientist at Honda Research Institute Europe, with the goal of finding novel applications of quantum computing from near-term to fault-tolerant quantum hardware. His scientific interest lay at the intersection of quantum physics and computer science, using tools from both fields to search for quantum advantage with existing quantum computers. Prior to joining HRI, he was awarded a research grant by the NWO to continue as research scientist at the Applied Quantum Algorithms group at Leiden University (the Netherlands). Xavi’s academic background includes a MSc in Physics, a PhD in theoretical physics from the Institut-Lorentz also from Leiden University.

About GECCO

GECCO Schedule at a Glance ([https://gecco-2025.sigevo.org/Program](https://gecco-2025.sigevo.org/Program))