Search Results

Documents authored by Kotthoff, Lars

Document
DOI: 10.4230/LIPIcs.CP.2026.38
On the Effect of Training Data Selection in Automated Algorithm Selection

Authors: Erdem Kuş, Özgür Akgün, Nguyen Dang, Lars Kotthoff, and Ian Miguel

Published in: LIPIcs, Volume 379, 32nd International Conference on Principles and Practice of Constraint Programming (CP 2026)

Abstract
Algorithms for solving combinatorial optimisation problems often exhibit complementary strengths, motivating automated algorithm selection by training ML models that predict the best algorithm for a given instance. However, collecting training data for such models is computationally expensive, as it requires running all provided algorithms on all training instances. Recent work on frugal algorithm selection shows that the training data collection cost can be reduced substantially through active learning, but the interaction between model choices and data efficiency remains poorly understood. In this work, we empirically investigate how different learning formulations behave under limited training data using the ASLib benchmark. Our results reveal that multiclass classification (MC), despite weak performance when trained on full training data, improves dramatically with active learning. Remarkably, active MC matches strong passive learners while using only a fraction of the training data. This highlights an unexpected efficiency gain: algorithm selectors that underperform with full training data become highly effective when training data is selected actively.
Cite as

Erdem Kuş, Özgür Akgün, Nguyen Dang, Lars Kotthoff, and Ian Miguel. On the Effect of Training Data Selection in Automated Algorithm Selection. In 32nd International Conference on Principles and Practice of Constraint Programming (CP 2026). Leibniz International Proceedings in Informatics (LIPIcs), Volume 379, pp. 38:1-38:22, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026)

Copy BibTex To Clipboard

@InProceedings{kus_et_al:LIPIcs.CP.2026.38,
  author =	{Ku\c{s}, Erdem and Akg\"{u}n, \"{O}zg\"{u}r and Dang, Nguyen and Kotthoff, Lars and Miguel, Ian},
  title =	{{On the Effect of Training Data Selection in Automated Algorithm Selection}},
  booktitle =	{32nd International Conference on Principles and Practice of Constraint Programming (CP 2026)},
  pages =	{38:1--38:22},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-432-1},
  ISSN =	{1868-8969},
  year =	{2026},
  volume =	{379},
  editor =	{Beldiceanu, Nicolas},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.CP.2026.38},
  URN =		{urn:nbn:de:0030-drops-266702},
  doi =		{10.4230/LIPIcs.CP.2026.38},
  annote =	{Keywords: Algorithm selection, Active learning, Learning strategies}
}
Document
DOI: 10.4230/DagRep.14.7.17
Automated Machine Learning For Computational Mechanics (Dagstuhl Seminar 24282)

Authors: Elena Raponi, Lars Kotthoff, Hyunsun Alicia Kim, and Marius Lindauer

Published in: Dagstuhl Reports, Volume 14, Issue 7 (2025)

Abstract
Machine learning (ML) has achieved undeniable success in computational mechanics, an ever-growing discipline that impacts all areas of engineering, from structural and fluid dynamics to solid mechanics and vehicle simulation. Computational mechanics uses numerical models and time- and resource-consuming simulations to reproduce physical phenomena, usually with the goal of optimizing the parameter configuration of the model with respect to the desired properties of the system. ML algorithms enable the construction of surrogate models that approximate the outcome of the simulations, allowing faster identification of well-performing configurations. However, determining the best ML approach for a given task is not straightforward and depends on human experts. Automated machine learning (AutoML) aims to reduce the need for experts to obtain effective ML pipelines. It provides off-the-shelf solutions that can be used without prior knowledge of ML, allowing engineers to spend more time on domain-specific tasks. AutoML is underutilized in computational mechanics; there is almost no communication between the two communities, and engineers spend unnecessary effort selecting and configuring ML algorithms. Our Dagstuhl Seminar aimed to (i) raise awareness of AutoML in the computational mechanics community, (ii) discover strengths and challenges for applying AutoML in practice, and (iii) create a bilateral exchange so that researchers can mutually benefit from their complementary goals and needs.
Cite as

Elena Raponi, Lars Kotthoff, Hyunsun Alicia Kim, and Marius Lindauer. Automated Machine Learning For Computational Mechanics (Dagstuhl Seminar 24282). In Dagstuhl Reports, Volume 14, Issue 7, pp. 17-34, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@Article{raponi_et_al:DagRep.14.7.17,
  author =	{Raponi, Elena and Kotthoff, Lars and Kim, Hyunsun Alicia and Lindauer, Marius},
  title =	{{Automated Machine Learning For Computational Mechanics (Dagstuhl Seminar 24282)}},
  pages =	{17--34},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2025},
  volume =	{14},
  number =	{7},
  editor =	{Raponi, Elena and Kotthoff, Lars and Kim, Hyunsun Alicia and Lindauer, Marius},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.14.7.17},
  URN =		{urn:nbn:de:0030-drops-229331},
  doi =		{10.4230/DagRep.14.7.17},
  annote =	{Keywords: automated algorithm design; computational mechanics; engineering applications of AI; black-box optimization; physics-informed machine learning}
}
Document
DOI: 10.4230/DagRep.13.9.116
Human-Centered Approaches for Provenance in Automated Data Science (Dagstuhl Seminar 23372)

Authors: Anamaria Crisan, Lars Kotthoff, Marc Streit, and Kai Xu

Published in: Dagstuhl Reports, Volume 13, Issue 9 (2024)

Abstract
The scope of automated machine learning (AutoML) technology has extended beyond its initial boundaries of model selection and hyperparameter tuning and towards end-to-end development and refinement of data science pipelines. These advances, both theoretical and realized, make the tools of data science more readily available to domain experts that rely on low- or no-code tooling options to analyze and make sense of their data. To ensure that automated data science technologies are applied both effectively and responsibly, it becomes increasingly urgent to carefully audit the decisions made both automatically and with guidance from humans. This Dagstuhl Seminar examines human-centered approaches for provenance in automated data science. While prior research concerning provenance and machine learning exists, it does not address the expanded scope of automated approaches and the consequences of applying such techniques at scale to the population of domain experts. In addition, most of the previous works focus on the automated part of this process, leaving a gap on the support for the sensemaking tasks users need to perform, such as selecting the datasets and candidate models and identifying potential causes for poor performance. The seminar brought together experts from across provenance, information visualization, visual analytics, machine learning, and human-computer interaction to articulate the user challenges posed by AutoML and automated data science, discuss the current state of the art, and propose directions for new research. More specifically, this seminar: - articulates the state of the art in AutoML and automated data science for supporting the provenance of decision making, - describes the challenges that data scientists and domain experts face when interfacing with automated approaches to make sense of an automated decision, - examines the interface between data-centric, model-centric, and user-centric models of provenance and how they interact with automated techniques, and - encourages exploration of human-centered approaches; for example leveraging visualization.
Cite as

Anamaria Crisan, Lars Kotthoff, Marc Streit, and Kai Xu. Human-Centered Approaches for Provenance in Automated Data Science (Dagstuhl Seminar 23372). In Dagstuhl Reports, Volume 13, Issue 9, pp. 116-136, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@Article{crisan_et_al:DagRep.13.9.116,
  author =	{Crisan, Anamaria and Kotthoff, Lars and Streit, Marc and Xu, Kai},
  title =	{{Human-Centered Approaches for Provenance in Automated Data Science (Dagstuhl Seminar 23372)}},
  pages =	{116--136},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2024},
  volume =	{13},
  number =	{9},
  editor =	{Crisan, Anamaria and Kotthoff, Lars and Streit, Marc and Xu, Kai},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.13.9.116},
  URN =		{urn:nbn:de:0030-drops-198236},
  doi =		{10.4230/DagRep.13.9.116},
  annote =	{Keywords: Dagstuhl Seminar, Provenance, AutoML, Data Science, Information Visualisation, Visual Analytics, Machine Learning, Human-Computer Interaction}
}
Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail
© 2023-2026 Schloss Dagstuhl – LZI GmbH Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact