Prof. Dr. Pascal Kerschke

Research Interests

Data Science
Machine Learning
Automated Algorithm Selection & Configuration
(Automated Machine Learning)
Optimization:
- Continuous (Black-Box) Optimization
- Multi-Objective Optimization
- Vehicle Routing
Benchmarking:
- Exploratory Landscape Analysis
- Visualization
- (Statistical) Performance Assessment
Interpretability of Algorithmic (Search and/or Decisions) Behavior
(Interpretable Machine Learning, Explainable AI)

Networks / Memberships

Coordinating founding member:

Benchmarking Network
COSEAL (Configuration and Selection of Algorithms)

Member and/or Supporter:

ACM SigEVO (Special Interest Group on Genetic and Evolutionary Computation der Association for Computing Machinery)
CLAIRE (Confederation of Laboratories for Artificial Intelligence Research in Europe)
DStatG (German Statistical Society)
ERCIS (European Research Center for Information Systems)
GfKl (Data Science Society)
GI (Computer Science Society)
IEEE CIS Task Force on Benchmarking

Publications

68 Entries

2022

BBE: Basin-Based Evaluation of Multimodal Multi-objective Optimization ProblemsHeins, J., Rook, J., Schäpermeier, L., Kerschke, P., Bossek, J. & Trautmann, H., 2022, Parallel Problem Solving from Nature – PPSN XVII - 17th International Conference, PPSN 2022, Proceedings. Rudolph, G., Kononova, A. V., Aguirre, H., Kerschke, P., Ochoa, G. & Tušar, T. (eds.).p. 192-206, 15 p.Electronic (full-text) versionResearch output: Contribution to book/conference proceedings/anthology/report > Conference contribution
HPO × ELA: Investigating Hyperparameter Optimization Landscapes by Means of Exploratory Landscape AnalysisSchneider, L., Schäpermeier, L., Prager, R. P., Bischl, B., Trautmann, H. & Kerschke, P., 2022, Parallel Problem Solving from Nature – PPSN XVII - 17th International Conference, PPSN 2022, Proceedings. Rudolph, G., Kononova, A. V., Aguirre, H., Kerschke, P., Ochoa, G. & Tušar, T. (eds.).p. 575-589, 15 p.Electronic (full-text) versionResearch output: Contribution to book/conference proceedings/anthology/report > Conference contribution
Parallel Problem Solving from Nature – PPSN XVII: 17th International Conference, PPSN 2022, Dortmund, Germany, September 10–14, 2022, Proceedings, Part IRudolph, G., Kononova, A. V., Aguirre, H., Kerschke, P., Ochoa, G. & Tušar, T., 2022, Springer, ChamElectronic (full-text) versionResearch output: Book/Report/Anthology > Monograph

2021

Towards Feature-Free Automated Algorithm Selection for Single-Objective Continuous Black-Box OptimizationPrager, R. P., Seiler, M. V., Trautmann, H. & Kerschke, P., 5 Dec 2021, 2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - ProceedingsElectronic (full-text) versionResearch output: Contribution to book/conference proceedings/anthology/report > Conference contribution
Peeking beyond peaks: Challenges and research potentials of continuous multimodal multi-objective optimizationGrimme, C., Kerschke, P., Aspar, P., Trautmann, H., Preuss, M., Deutz, A. H., Wang, H. & 1 others, Dec 2021, In: Computers and Operations Research. 136, 105489Electronic (full-text) versionResearch output: Contribution to journal > Research article
On the potential of normalized TSP features for automated algorithm selectionHeins, J., Bossek, J., Pohl, J., Seiler, M., Trautmann, H. & Kerschke, P., 6 Sep 2021, FOGA 2021 - Proceedings of the 16th ACM/SIGEVO Conference on Foundations of Genetic AlgorithmsElectronic (full-text) versionResearch output: Contribution to book/conference proceedings/anthology/report > Conference contribution
Lifting the Multimodality-Fog in Continuous Multi-objective OptimizationKerschke, P. & Grimme, C., 2021, Natural Computing Series. p. 89-111, 23 p.Electronic (full-text) versionResearch output: Contribution to book/conference proceedings/anthology/report > Chapter in book/Anthology/Report
Multi ³: Optimizing Multimodal Single-Objective Continuous Problems in the Multi-objective Space by Means of MultiobjectivizationAspar, P., Kerschke, P., Steinhoff, V., Trautmann, H. & Grimme, C., 2021, Evolutionary Multi-Criterion Optimization - 11th International Conference, EMO 2021, Proceedings. Ishibuchi, H., Zhang, Q., Cheng, R., Li, K., Li, H., Wang, H. & Zhou, A. (eds.).p. 311-322, 12 p.Electronic (full-text) versionResearch output: Contribution to book/conference proceedings/anthology/report > Conference contribution
To Boldly Show What No One Has Seen Before: A Dashboard for Visualizing Multi-objective LandscapesSchäpermeier, L., Grimme, C. & Kerschke, P., 2021, Evolutionary Multi-Criterion Optimization - 11th International Conference, EMO 2021, Proceedings. Ishibuchi, H., Zhang, Q., Cheng, R., Li, K., Li, H., Wang, H. & Zhou, A. (eds.).p. 632-644, 13 p.Electronic (full-text) versionResearch output: Contribution to book/conference proceedings/anthology/report > Conference contribution

2020

Multiobjectivization of Local Search: Single-Objective Optimization Benefits From Multi-Objective Gradient DescentSteinhoff, V., Kerschke, P., Aspar, P., Trautmann, H. & Grimme, C., 1 Dec 2020, 2020 IEEE Symposium Series on Computational Intelligence (SSCI)Electronic (full-text) versionResearch output: Contribution to book/conference proceedings/anthology/report > Conference contribution
Per-Instance Configuration of the Modularized CMA-ES by Means of Classifier Chains and Exploratory Landscape AnalysisPrager, R. P., Trautmann, H., Wang, H., Bäck, T. H. W. & Kerschke, P., 1 Dec 2020, 2020 IEEE Symposium Series on Computational Intelligence (SSCI)Electronic (full-text) versionResearch output: Contribution to book/conference proceedings/anthology/report > Conference contribution
Enhancing Resilience of Deep Learning Networks by Means of Transferable AdversariesSeiler, M., Trautmann, H. & Kerschke, P., 28 Sep 2020, 2020 International Joint Conference on Neural Networks (IJCNN)Electronic (full-text) versionResearch output: Contribution to book/conference proceedings/anthology/report > Conference contribution
Anytime Behavior of Inexact TSP Solvers and Perspectives for Automated Algorithm SelectionBossek, J., Kerschke, P. & Trautmann, H., 3 Sep 2020, 2020 IEEE Congress on Evolutionary Computation (CEC)Electronic (full-text) versionResearch output: Contribution to book/conference proceedings/anthology/report > Conference contribution
The Node Weight Dependent Traveling Salesperson Problem: Approximation Algorithms and Randomized Search HeuristicsBossek, J., Casel, K., Kerschke, P. & Neumann, F., 26 Jun 2020, 2020 Genetic and Evolutionary Computation ConferenceElectronic (full-text) versionResearch output: Contribution to book/conference proceedings/anthology/report > Conference contribution
Initial design strategies and their effects on sequential model-based optimization: an exploratory case study based on BBOBBossek, J., Doerr, C. & Kerschke, P., 25 Jun 2020, Proceedings of the 2020 Genetic and Evolutionary Computation ConferenceElectronic (full-text) versionResearch output: Contribution to book/conference proceedings/anthology/report > Conference contribution
A multi-objective perspective on performance assessment and automated selection of single-objective optimization algorithmsBossek, J., Kerschke, P. & Trautmann, H., Mar 2020, In: Applied soft computing : the official journal of the World Federation on Soft Computing (WFSC). 88, 105901Electronic (full-text) versionResearch output: Contribution to journal > Research article
Deep Learning as a Competitive Feature-Free Approach for Automated Algorithm Selection on the Traveling Salesperson ProblemSeiler, M., Pohl, J., Bossek, J., Kerschke, P. & Trautmann, H., 2020, Parallel Problem Solving from Nature – PPSN XVIElectronic (full-text) versionResearch output: Contribution to book/conference proceedings/anthology/report > Conference contribution
Evolving Sampling Strategies for One-Shot Optimization TasksBossek, J., Doerr, C., Kerschke, P., Neumann, A. & Neumann, F., 2020, Parallel Problem Solving from Nature – PPSN XVIElectronic (full-text) versionResearch output: Contribution to book/conference proceedings/anthology/report > Conference contribution
One PLOT to Show Them All: Visualization of Efficient Sets in Multi-objective LandscapesSchäpermeier, L., Grimme, C. & Kerschke, P., 2020, 16th International Conference on Parallel Problem Solving from NatureElectronic (full-text) versionResearch output: Contribution to book/conference proceedings/anthology/report > Conference contribution

2019

Search Dynamics on Multimodal Multiobjective ProblemsKerschke, P., Wang, H., Preuss, M., Grimme, C., Deutz, A. H., Trautmann, H. & Emmerich, M. T. M., Dec 2019, In: Evolutionary Computation. 27, 4, p. 577–609Electronic (full-text) versionResearch output: Contribution to journal > Research article
OpenML: An R package to connect to the machine learning platform OpenMLCasalicchio, G., Bossek, J., Lang, M., Kirchhoff, D., Kerschke, P., Hofner, B., Seibold, H. & 2 others, Sep 2019, In: Computational statistics. 34, p. 977–991Electronic (full-text) versionResearch output: Contribution to journal > Research article
Evolving diverse TSP instances by means of novel and creative mutation operatorsBossek, J., Kerschke, P., Neumann, A., Wagner, M. & Neumann, F., 27 Aug 2019, 15th ACM/SIGEVO Conference on Foundations of Genetic Algorithms - FOGA '19Electronic (full-text) versionResearch output: Contribution to book/conference proceedings/anthology/report > Conference contribution
Exploratory Landscape AnalysisKerschke, P. & Preuss, M., 13 Jul 2019, GECCO '19: Proceedings of the Genetic and Evolutionary Computation Conference Companion. p. 1137–1155Electronic (full-text) versionResearch output: Contribution to book/conference proceedings/anthology/report > Conference contribution
Exploring the MLDA benchmark on the nevergrad platformRapin, J., Gallagher, M., Kerschke, P., Preuss, M. & Teytaud, O., 13 Jul 2019, Genetic and Evolutionary Computation Conference (GECCO) CompanionElectronic (full-text) versionResearch output: Contribution to book/conference proceedings/anthology/report > Conference contribution
Making a case for (Hyper-)parameter tuning as benchmark problemsDoerr, C., Dreo, J. & Kerschke, P., 13 Jul 2019, Genetic and Evolutionary Computation Conference (GECCO) CompanionElectronic (full-text) versionResearch output: Contribution to book/conference proceedings/anthology/report > Conference contribution

Professional Career

since 2021:
Chair for Big Data Analytics in Transportation,
"Friedrich List" Faculty of Transport and Traffic Sciences, Technische Universität Dresden, Dresden, Germany
since 2019:
Lecturer in the Master Degree Program IT-Management,
WWU Weiterbildung, Münster, Germany
since 2019:
Lecturer in the Certificate Degree Program Data Science,
WWU Weiterbildung, Münster, Germany
2017 - 2021:
Postdoctoral Researcher at the Chair of Data Science: Statistics & Optimization,
Department of Information Systems, University of Münster, Münster, Germany
2017 - 2020:
Lecturer in the Degree Program Business Administration and Taxes,
University of Applied Sciences Münster, Münster, Germany
2013 - 2017:
Research Associate at the Chair of Data Science: Statistics & Optimization,
Department of Information Systems, University of Münster, Münster, Germany

Education

2013 - 2017:
Doctoral Studies (Dr. rer. pol.) at the Department of Information Systems,
School of Business and Economics, University of Münster, Münster, Germany
- Title of PhD Thesis: Automated and Feature-Based Problem Characterization and Algorithm Selection Through Machine Learning
2010 - 2013:
Data Science (M.Sc.), TU Dortmund University, Dortmund, Germany
2011:
Semester Abroad (ERASMUS) at the University of Bergen, Bergen, Norway
2007 - 2010:
Data Analysis and Management (B.Sc.), TU Dortmund University, Dortmund, Germany

Awards and Prizes

07/2025:
Nominated for the Best Paper Award in the ECOM Track of GECCO (2025),
Organizing Committee of GECCO 2025
- Nominated Publication:
  Jonathan Heins, Darrell Whitley and Pascal Kerschke (2025). To Repair or Not to Repair? Investigating the Importance of AB-Cycles for the State-of-the-Art TSP Heuristic EAX. Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), ACM.
  Preprint available on arXiv: https://www.arxiv.org/abs/2505.00803
09/2024:
PPSN XVIII Best Paper Award (2024),
University of Applied Sciences Upper Austria and Organizing Committee of PPSN XVIII
- Awarded Publication:
  Lennart Schäpermeier and Pascal Kerschke (2024). Reinvestigating the R2 Indicator: Achieving Pareto Compliance by Integration. International Conference on Parallel Problem Solving from Nature (PPSN XVIII), S. 202 - 216, Springer.
09/2021:
Runner-Up of the FOGA XVI Best Paper Award (2021),
FH Vorarlberg and Organizing Committee of FOGA XVI
- Nominated Publication:
  Jonathan Heins, Jakob Bossek, Janina Pohl, Moritz Seiler, Heike Trautmann and Pascal Kerschke (2021). On the Potential of Normalized TSP Features for Automated Algorithm Selection. 16th ACM/SIGEVO Conference on Foundations of Genetic Algorithms (FOGA XVI), pp. 1 - 15, ACM.
12/2018:
Dissertation Prize of the School of Business and Economics,
University of Münster, Münster, Germany
09/2018:
Invited Young Researcher at the 6th Heidelberg Laureate Forum,
Heidelberg Laureate Forum Foundation
09/2016:
PPSN XIV Best Paper Award (2016),
Edinburgh Napier University and Organizing Committee of PPSN XIV
- Awarded Publication:
  Pascal Kerschke, Hao Wang, Mike Preuss, Christian Grimme, André Deutz, Heike Trautmann, Michael Emmerich (2016). Towards Analyzing Multimodality of Continuous Multiobjective Landscapes. International Conference on Parallel Problem Solving from Nature (PPSN XIV), pp. 962 - 972, Springer.

Prof. Dr. Pascal Kerschke

2022

2021

2020

2019

About this page

Einblicke ins Studium