Benchmarking@GECCO-2025 Workshop
Good Benchmarking Practices for Evolutionary Computation
Time and location: tba
hybrid event : onsite in Málaga, Spain, and online
register here
register here
A platform to come together and to discuss recent progress and challenges in the area of benchmarking optimization heuristics.
This workshop will continue our workshop series that we started in 2020. The core theme is on benchmarking evolutionary computation methods and related sampling-based optimization heuristics, but each year, we will change the focus.
For GECCO 2025, our focus will be on “Benchmarking for humans and machines - Differences and Similarities”.
Many currently popular benchmarks are designed to be interpretable by humans with specific questions in mind. For example, if the algorithm can exploit separability or how it handles disconnected Pareto fronts. As a result, they do not attempt to cover the full space of interesting problems. However, when used in the context of automated algorithm selection, algorithm configuration, and similar machine learning tasks, data requirements may change, as the ability for manual interpretation is no longer a restriction.
At the same time, benchmarking results in publications are often presented as aggregates without heeding the original intent of the benchmark designer. So even without the involvement of machines, the benchmarking data is typically suboptimally presented and interpreted.
In this workshop, we will be addressing the following questions:
What are key similarities and differences between benchmarks designed for human vs. machine interpretation?
Are there inherent differences between human vs. machine interpretable benchmarking pipelines that require the experimental setup, apart from the size of the generated data sets, to be different?
How can we best support the analysis of benchmarking data, for manual interpretation and machine-based learning.
Nikolaus Hansen (Inria / Institute Polytechnique de Paris, France): Revisiting COCO with automated benchmarking in mind (20 Minutes)
Discussion (15 Minutes)
Antoine Cully (Imperial College London, UK): Benchmarking through the lense of a Machine Learner and Roboticist (20 Minutes)
Discussion (15 minutes)
Panel Discussion and Action Items (40 Minutes)
Antoine Cully (Imperial College London, UK)
Emma Hart (Edinburgh Napier University, UK)
Nikolaus Hansen (Inria, France)
Tea Tušar (Jožef Stefan Institute, Slovenia)
Abstract: This presentation gives a quick overview over the defining features for benchmarking within the COCO platform. We then investigate whether and in what sense these features are specific to human benchmarking and finally discuss some ideas for how some aspects could or should be carefully adapted for an automated benchmarking setting.
Speaker: Nikolaus Hansen is a research director at Inria and the Institut Polytechnique de Paris, France. His main research areas are 1) randomized search algorithms for continuous, high-dimensional search spaces, 2) learning and adaptation with the application in evolutionary computation, and 3) methodologies for a meaningful performance assessment and comparison of search algorithms. His research is driven by the eventual goal to develop algorithms applicable in practice.
Antoine Cully is Lecturer (Assistant Professor) at Imperial College London (United Kingdom). His research is at the intersection between artificial intelligence and robotics. He applies machine learning approaches, like evolutionary algorithms, on robots to increase their versatility and their adaptation capabilities. In particular, he has recently developed Quality-Diversity optimization algorithms to enable robots to autonomously learn large behavioural repertoires. For instance, this approach enabled legged robots to autonomously learn how to walk in every direction or to adapt to damage situations. Antoine Cully received the M.Sc. and the Ph.D. degrees in robotics and artificial intelligence from the Sorbonne Université in Paris, France, in 2012 and 2015, respectively, and the engineer degree from the School of Engineering Polytech’Sorbonne, in 2012. His Ph.D. dissertation has received three Best-Thesis awards. He has published several journal papers in prestigious journals including Nature, IEEE Transaction in Evolutionary Computation, and the International Journal of Robotics Research. His work was featured on the cover of Nature (Cully et al., 2015), received the "Outstanding Paper of 2015" award from the Society for Artificial Life (2016), the French "La Recherche" award (2016), and two Best-Paper awards from GECCO (2021, 2022).
Prof. Hart gained a 1st Class Honours Degree in Chemistry from the University of Oxford, followed by an MSc in Artificial Intelligence from the University of Edinburgh. Her PhD, also from the University of Edinburgh, explored the use of immunology as an inspiration for computing, examining a range of techniques applied to optimisation and data classification problems. She moved to Edinburgh Napier University in 2000 as a lecturer, and was promoted to a Chair in 2008 where she leads a group in Nature-Inspired Intelligent Systems, specialising in optimisation and learning algorithms applied in domains that range from combinatorial optimisation to robotics. Her work mainly involves development of algorithms inspired by biological evolution to discover novel solutions to challenging problems. She was appointed as Editor-in-Chief of Evolutionary Computation (MIT Press) in 2017. She has been invited to give keynotes at major international conferences including CLAIO 2020, IEEE CEC 2019, EURO 2016 and UKCI 2015 and was General Chair of PPSN 2016, and as a Track Chair at GECCO for several years. She is an elected member of the Executive Board of the ACM SIG on Evolutionary Computation. More broadly, she invited member of the UK Operations Research Society Research Panel, and in Scotland, co-leads the Artificial Intelligence theme within SICSA. She was appointed as a panel member for REF2021 (UoA11 Computer Science). In 2020 she was appointed to the Steering Committee that developed Scotland's AI Strategy published in 2021 . She has a sustained track record of obtaining funding from the EU, EPSRC and of engaging with industry via KTP projects and consultancy, and participates enthusiastically in public-engagement activity, e.g Pint of Science. Her work in evolutionary robotics has attracted significant media attention, e.g. in New Scientist, the Guardian, Telegraph and the Conversation. In 2021, she gave a TED Talk on Evolutionary Robotics, available online
Nikolaus Hansen is a research director at Inria and the Institut Polytechnique de Paris, France. His main research areas are 1) randomized search algorithms for continuous, high-dimensional search spaces, 2) learning and adaptation with the application in evolutionary computation, and 3) methodologies for a meaningful performance assessment and comparison of search algorithms. His research is driven by the eventual goal to develop algorithms applicable in practice.
Tea Tušar is a senior research associate at the Department of Intelligent Systems at the Jožef Stefan Institute and an assistant professor at the Jožef Stefan International Postgraduate School. She received her PhD for her work on visualizing solution sets in multi-objective optimization. Following her doctorate, she completed a postdoctoral fellowship at Inria Lille, France, where she contributed to benchmarking multi-objective optimization algorithms. Her work focuses on Evolutionary Computation, with a particular emphasis on visualizing and benchmarking the results of evolutionary algorithms for both single- and multi-objective optimization, with and without constraints, and applying these methods to solve real-world optimization problems
Vanessa Volz (CWI, Amsterdam, The Netherlands)
Carola Doerr (CNRS researcher at Sorbonne University, Paris, France)
Boris Naujoks (TH Cologne, Germany)
Mike Preuss (LIACS, Leiden University)
Olaf Mersmann (HS Bund, Brühl, Germany)
Pascal Kerschke (TU Dresden, Germany)
The Genetic and Evolutionary Computation Conference (GECCO 2025), which will be held as a hybrid event (online & onsite in Málaga, Spain)