Jonas Wahl

he/himJonas Wahl

Senior Researcher
Group Leader Causal Models and Representations (CaMoRe)
Professor II for Causal Analysis and Artificial Intelligence (University of Bergen)

DFKI – Neuro-Mechanistic Modeling

CaMoRe – Causal Models and Representations

University of Bergen

CERTAIN – Center for European Research in Trusted AI

DFKI Labor Berlin

Kesselhaus in der Lanolinfabrik - Salzufer 15/16

10587 Berlin

Germany

About Me

Originally trained as a mathematician, I have become interested in causal inference through the famous ‘Book of Why’. Nowadays, my research focuses on causal discovery evaluation, causal abstraction, causally informed sequential decision making, as well as methods that combine experimental and observational data for inference. I like to work together closely with domain scientists; at the moment I focus on applications in ecology and health, but I am open to working in other domains. If you want to collaborate, please get in touch!

I am one of the project leaders of the MAC-MERLin project and the head of the research group Causal Models and Representations (CaMoRe). Since February 2026, I am also a part-time Professor II for AI and Causal Analysis at the University of Bergen, Norway.

Before joining DFKI in 2025, I was a postdoctoral researcher at TU Berlin (2022–2024, with Prof. Jakob Runge), working on causal inference for spatio-temporal data in climate science, the evaluation of causal discovery, and the statistical foundations of causal inference. Before that, I was a postdoc at the Hausdorff Center for Mathematics in Bonn (2019–2022), working on stochastic processes on branching graphs and random walks in algebras, after completing my Ph.D. in mathematics at KU Leuven (2018) under the supervision of Prof. Stefaan Vaes.

Other Work / Research Activity

Scientific Community Service

  • Guest editor (2025–2027) of a special issue on Causal Inference in Ecology and Evolutionary Biology in Philosophical Transactions of the Royal Society B.
  • Workshop and conference organization:
    • Saarbrücken Causality Workshop (DFKI, October 2026), co-organized with researchers from DFKI and CISPA.
    • CAESAR – Causal Anomalies: Exploring Synergies of Anomaly Detection and Causal Inference at ECML PKDD 2026 (Naples), co-organized with the DLR Institute of Data Science in Jena.
    • CI4TS – Causal Inference for Time Series at UAI 2023 (Pittsburgh) and UAI 2024 (Barcelona).
    • Young Women in C*-algebras and Young Mathematicians in C*-algebras 2018 (KU Leuven).
    • Program committee of STCausal 2024, the 1st ACM SIGSPATIAL International Workshop on Spatiotemporal Causal Analysis (Atlanta).
  • Reviewer for NeurIPS, ICML, AAAI, UAI, CLeaR, Science Advances, Nature Communications, Chaos, Journal of Causal Inference, Annals of Epidemiology, IEEE Transactions on Signal Processing and Communications in Mathematical Physics.
  • I am a member of Algoright e.V..

Previous Affiliations

  • Fellow at the Centre for Interdisciplinary Research (ZiF) Bielefeld within the focus program Mapping Evidence to Theory in Ecology (2024).
  • Associated member of the ELLIS Unit Jena (2023–2024).
  • Long-term guest researcher at the German Aerospace Center (DLR) in Jena (2022–2024).

Selected Talks

  • Isaac Newton Institute, University of Cambridge, March 2026
  • Einstein Circle Berlin, Charité, February 2026
  • IKIM Essen, December 2025
  • Winter School on Causality and Explainable AI, Paris, October 2025
  • University of Nancy, September 2025
  • Symposium on Causal Inference, University of Potsdam, June 2025
  • Workshop Addressing the Challenges of Generalization and Causality, University of Bielefeld, November 2024
  • Statistics Seminar, University College Dublin, October 2024
  • Workshop Causal and Safe Reinforcement Learning, DFKI Saarbrücken, May 2024
  • Workshop Causal Spatial Data Analysis, Schloss Dagstuhl, May 2024
  • Workshop Taming Complexity in Ecology, February 2024
  • Statistics Seminar, HU Berlin, January 2024
  • Workshop Fundamental Challenges in Causality, University of Grenoble, May 2023
  • USMILE Workshop, University of Valencia, October 2022

Interests

Originally trained as a mathematician, I have become interested in causal inference through the famous ‘Book of Why’. Nowadays, my research focuses on causal discovery evaluation, causal abstraction, causally informed sequential decision making, as well as methods that combine experimental and observational data for inference. I like to work together closely with domain scientists; at the moment I focus on applications in ecology and health, but I am open to working in other domains. If you want to collaborate, please get in touch!
  • Causal Inference
  • Causal Discovery
  • Evaluation and Benchmarking
  • Causal Abstraction
  • Causal Sequential Decision Making
  • Applications in Health
  • Applications in Ecology

Education

  • Doctor of Science (Ph.D.) in Mathematics, 2018

    Supervised by Prof. Stefaan Vaes at KU Leuven, Belgium

    Nonsingular Bernoulli actions and quantum symmetries

  • Master of Science in Mathematics, 2014

    Saarland University, Germany

  • Bachelor of Science in Mathematics, 2012

    Saarland University, Germany

Publications (16)

2026

3 papers

How PC-based Methods Err: Towards Better Reporting of Assumption Violations and Small Sample Errors

2026 — Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence

@inproceedings{faltenbacherHowPCBasedMethodsErr2026,
 author = {Faltenbacher, Sofia and Wahl, Jonas and Herman, Rebecca Jean and Runge, Jakob},
 booktitle = {Proceedings of the 42nd Conference on Uncertainty in Artificial Intelligence},
 editor = {Perković, Emilija and Malinsky, Daniel},
 month = {Aug},
 pages = {1498--1519},
 pdf = {https://raw.githubusercontent.com/mlresearch/v337/main/assets/faltenbacher26a/faltenbacher26a.pdf},
 publisher = {PMLR},
 series = {Proceedings of Machine Learning Research},
 title = {How PC-based Methods Err: Towards Better Reporting of Assumption Violations and Small Sample Errors},
 url = {https://proceedings.mlr.press/v337/faltenbacher26a.html},
 volume = {337},
 year = {2026}
}
URL

Chaotic and complex dynamics expose the limits of counterfactual reasoning

2026 — Scientific Reports (Sci Rep)

@article{aalailaChaoticAndComplexDynamics2026,
 author = {Yahya Aalaila and Gerrit Großmann and Sumantrak Mukherjee and Jonas Wahl and Sebastian Vollmer},
 doi = {10.1038/s41598-026-52349-2},
 journal = {Scientific Reports (Sci Rep)},
 month = {6},
 number = {1},
 pages = {1-14},
 publisher = {Springer Nature},
 title = {Chaotic and complex dynamics expose the limits of counterfactual reasoning},
 url = {https://www.nature.com/articles/s41598-026-52349-2},
 volume = {16},
 year = {2026}
}
DOI URL

Causal inference on process graphs: Causal structure and effect identification

2026 — Bernoulli

PDF
@article{reiterCausalInferenceOnProcess2026,
 author = {Nicolas-Domenic Reiter and Jonas Wahl and Andreas Gerhardus and Jakob Runge},
 doi = {10.3150/25-BEJ1909},
 journal = {Bernoulli},
 month = {5},
 number = {2},
 pages = {1356-1382},
 publisher = {Bernoulli Society for Mathematical Statistics and Probability},
 title = {Causal inference on process graphs: Causal structure and effect identification},
 url = {https://www.dfki.de/fileadmin/user_upload/import/16775_casual_inference_on_process_graphs.pdf},
 volume = {32},
 year = {2026}
}
DOI

2025

5 papers

Sortability of Time Series Data

2025 — Transactions on Machine Learning Research (TMLR)

PDF
@article{lohseSortabilityOfTimeSeries2025,
 author = {Christopher Lohse and Jonas Wahl},
 editor = {Adam Arany},
 journal = {Transactions on Machine Learning Research (TMLR)},
 month = {7},
 pages = {---},
 publisher = {-},
 title = {Sortability of Time Series Data},
 url = {https://openreview.net/forum?id=OGvmCpcHdV},
 volume = {-},
 year = {2025}
}
URL

Structural Causal Bottleneck Models

2025 — UAI 2025 Workshop on Causal Abstractions and Representations. Causal Abstractions and Representations (CAR), located at UAI 2025, July 25, Rio de Janeiro, Brazil

@inproceedings{bingStructuralCausalBottleneckModels2025,
 author = {Simon Bing and Jonas Wahl and Jakob Runge},
 booktitle = {UAI 2025 Workshop on Causal Abstractions and Representations. Causal Abstractions and Representations (CAR), located at UAI 2025, July 25, Rio de Janeiro, Brazil},
 month = {6},
 publisher = {OpenReview},
 title = {Structural Causal Bottleneck Models},
 url = {https://openreview.net/forum?id=EFNvKMSITB},
 year = {2025}
}
URL

Separation-Based Distance Measures for Causal Graphs

2025 — Proceedings of The 28th International Conference on Artificial Intelligence and Statistics. International Conference on Artificial Intelligence and Statistics (AISTATS-2025), May 3-5, Mai Khao, Thailand

PDF
@inproceedings{wahlSeparationBasedDistanceMeasuresFor2025,
 author = {Jonas Wahl and Jakob Runge},
 booktitle = {Proceedings of The 28th International Conference on Artificial Intelligence and Statistics. International Conference on Artificial Intelligence and Statistics (AISTATS-2025), May 3-5, Mai Khao, Thailand},
 pages = {3412-3420},
 publisher = {Proceedings of Machine Learning Research},
 title = {Separation-Based Distance Measures for Causal Graphs},
 url = {https://proceedings.mlr.press/v258/wahl25b.html},
 volume = {258},
 year = {2025}
}
URL

The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applications

2025 — Proceedings of the Fourth Conference on Causal Learning and Reasoning. Conference on Causal Learning and Reasoning (CLeaR-2025)

PDF
@inproceedings{brouillardTheLandscapeOfCausal2025,
 author = {Philippe Brouillard and Chandler Squires and Jonas Wahl and Konrad Körding and Karen Sachs and Alexandre Drouin and Dhanya Sridhar},
 booktitle = {Proceedings of the Fourth Conference on Causal Learning and Reasoning. Conference on Causal Learning and Reasoning (CLeaR-2025)},
 organization = {PMLR},
 pages = {834-873},
 publisher = {MLResearchPress},
 title = {The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applications},
 url = {https://proceedings.mlr.press/v275/brouillard25a},
 volume = {275},
 year = {2025}
}
URL

Unitless Unrestricted Markov-Consistent SCM Generation: Better Benchmark Datasets for Causal Discovery

2025 — Proceedings of the Fourth Conference on Causal Learning and Reasoning. Conference on Causal Learning and Reasoning (CLeaR-2025)

PDF
@inproceedings{hermanUnitlessUnrestrictedMarkovConsistentSCM2025,
 author = {Rebecca J Herman and Jonas Wahl and Urmi Ninad and Jakob Runge},
 booktitle = {Proceedings of the Fourth Conference on Causal Learning and Reasoning. Conference on Causal Learning and Reasoning (CLeaR-2025)},
 pages = {1506-1531},
 publisher = {MLResearchPress},
 title = {Unitless Unrestricted Markov-Consistent SCM Generation: Better Benchmark Datasets for Causal Discovery},
 url = {https://proceedings.mlr.press/v275/herman25a.html},
 volume = {275},
 year = {2025}
}
URL

2024

2 papers

Identifying Linearly-Mixed Causal Representations from Multi-Node Interventions

2024 — Proceedings of the Third Conference on Causal Learning and Reasoning. Conference on Causal Learning and Reasoning (CLeaR-2024)

@inproceedings{bingIdentifyingLinearlyMixedCausalRepresentations2024,
 author = {Simon Bing and Urmi Ninad and Jonas Wahl and Jakob Runge},
 booktitle = {Proceedings of the Third Conference on Causal Learning and Reasoning. Conference on Causal Learning and Reasoning (CLeaR-2024)},
 editor = {Francesco Locatello and Vanessa Didelez},
 month = {4},
 pages = {843-867},
 publisher = {PMLR},
 series = {Proceedings of Machine Learning Research},
 title = {Identifying Linearly-Mixed Causal Representations from Multi-Node Interventions},
 url = {https://proceedings.mlr.press/v236/bing24a.html},
 volume = {236},
 year = {2024}
}
URL

Causal Inference for Spatial Data Analytics (Dagstuhl Seminar 24202)

2024 — Dagstuhl Reports

@article{tomkoCausalInferenceForSpatial2024,
 author = {Martin Tomko and Yanan Xin and Jonas Wahl},
 doi = {10.4230/DagRep.14.5.25},
 editor = {Martin Tomko and Yanan Xin and Jonas Wahl},
 journal = {Dagstuhl Reports},
 number = {5},
 pages = {25-57},
 publisher = {Schloss Dagstuhl -- Leibniz-Zentrum für Informatik, Dagstuhl, Germany},
 title = {Causal Inference for Spatial Data Analytics (Dagstuhl Seminar 24202)},
 url = {https://drops.dagstuhl.de/entities/document/10.4230/DagRep.14.5.25},
 volume = {14},
 year = {2024}
}
DOI URL

2023

1 paper

Vector Causal Inference between Two Groups of Variables

2023 — Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)

@article{wahlVectorCausalInferenceBetween2023,
 author = {Jonas Wahl and Urmi Ninad and Jakob Runge},
 doi = {10.1609/aaai.v37i10.26450},
 journal = {Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)},
 month = {6},
 number = {10},
 pages = {12305-12312},
 publisher = {AAAI Press},
 title = {Vector Causal Inference between Two Groups of Variables},
 url = {https://ojs.aaai.org/index.php/AAAI/article/view/26450},
 volume = {37},
 year = {2023}
}
DOI URL

2022

3 papers

Where are all the guns? Modeling firearm ownership in the United States

2022 — Patterns

@article{wahlWhereAreAllThe2022,
 author = {Jonas Wahl},
 doi = {10.1016/j.patter.2022.100571},
 journal = {Patterns},
 month = {8},
 number = {8},
 pages = {1-2},
 publisher = {Elsevier},
 title = {Where are all the guns? Modeling firearm ownership in the United States},
 url = {https://www.cell.com/patterns/fulltext/S2666-3899(22)00182-9},
 volume = {3},
 year = {2022}
}
DOI URL

Traces on diagram algebras I: Free partition quantum groups, random lattice paths and random walks on trees

2022 — Journal of the London Mathematical Society

@article{wahlTracesOnDiagramAlgebras2022,
 author = {Jonas Wahl},
 doi = {10.1112/jlms.12562},
 journal = {Journal of the London Mathematical Society},
 month = {3},
 number = {4},
 pages = {2324-2372},
 publisher = {John Wiley & Sons, Ltd},
 title = {Traces on diagram algebras I: Free partition quantum groups, random lattice paths and random walks on trees},
 url = {https://londmathsoc.onlinelibrary.wiley.com/doi/full/10.1112/jlms.12562},
 volume = {105},
 year = {2022}
}
DOI URL

Conditional Independence Testing with Heteroskedastic Data and Applications to Causal Discovery

2022 — Advances in Neural Information Processing Systems 35. Neural Information Processing Systems (NeurIPS-2022), 36th Conference, November 28 - December 9

PDF
@inproceedings{guntherConditionalIndependenceTestingWith2022,
 author = {Wiebke Günther and Urmi Ninad and Jonas Wahl and Jakob Runge},
 booktitle = {Advances in Neural Information Processing Systems 35. Neural Information Processing Systems (NeurIPS-2022), 36th Conference, November 28 - December 9},
 editor = {S. Koyejo and S. Mohamed and A. Agarwal and D. Belgrave and K. Cho and A. Oh},
 isbn = {9781713871088},
 pages = {16191-16202},
 publisher = {Curran Associates, Inc.},
 title = {Conditional Independence Testing with Heteroskedastic Data and Applications to Causal Discovery},
 url = {https://proceedings.neurips.cc/paper_files/paper/2022/file/6739d8df16b5bce3587ca5f18662a6aa-Paper-Conference.pdf},
 year = {2022}
}

2018

1 paper

Nonsingular Bernoulli actions & quantum symmetries

2018 — ARENBERG DOCTORAL SCHOOL Faculty of Science

@phdthesis{wahlNonsingularBernoulliActionsQuantum2018,
 author = {Jonas Wahl},
 month = {6},
 school = {ARENBERG DOCTORAL SCHOOL Faculty of Science},
 title = {Nonsingular Bernoulli actions & quantum symmetries},
 type = {PhD-Thesis},
 url = {https://www.dfki.de/fileadmin/user_upload/import/17047_thesis_(1).pdf},
 year = {2018}
}

2015

1 paper

A note on reduced and von Neumann algebraic free wreath products

2015 — Illinois Journal of Mathematics (IJM)

@article{wahlANoteOnReduced2015,
\wr_{\ast} S_N^+$, where $\mathbb{G}$ is a compact matrix quantum group. Based on recent results on their corepresentation theory by Lemeux and Tarrago in [Lemeux and Tarrago (2014)], we prove that $\mathbb{G} \wr_{\ast} S_N^+$ is of Kac type whenever $\mathbb{G}$ is, and that the reduced version of $\mathbb{G} \wr_{\ast} S_N^+$ is simple with unique trace state whenever $N \geq 8$. Moreover, we prove that the reduced von Neumann algebra of $\mathbb{G} \wr_{\ast} S_N^+$ does not have property $\Gamma$.},
 author = {Jonas Wahl},
 doi = {10.1215/ijm/1475266409},
 journal = {Illinois Journal of Mathematics (IJM)},
 number = {3},
 pages = {801-817},
 publisher = {Duke University Press (im Auftrag der University of Illinois)},
 title = {A note on reduced and von Neumann algebraic free wreath products},
 url = {https://projecteuclid.org/journals/illinois-journal-of-mathematics/volume-59/issue-3/A-note-on-reduced-and-von-Neumann-algebraic-free-wreath/10.1215/ijm/1475266409.full},
 volume = {59},
 year = {2015}
}
DOI URL

Teaching (6)

  • Spatiotemporal Models and Inference

    Lecturer (English), in Summer 2025
    Seminar at Saarland University

  • Causal Inference

    Lecturer (Joint With Prof. Jakob Runge and Dr. Urmi Ninad) (English), in Winter 2023/24
    Lecture at TU Berlin

  • Causal Inference

    Lecturer (Joint With Prof. Jakob Runge and Dr. Urmi Ninad) (English), in Winter 2022/23
    Lecture at TU Berlin

  • Probability Theory I

    External Lecturer (Dutch), in Summer 2020
    Lecture at KU Leuven

  • Integrable Probability

    Substitute Lecturer (4 of 16 Lectures)
    Lecture at HCM Bonn

  • Functional Analysis II

    Guest Lecturer (5 Lectures), in Winter 2015/16
    Lecture at Saarland University

Supervised Students (12)

  • Pascal Schumann

    PhD Thesis, ongoing

  • Felix Jahn

    PhD Thesis, ongoing

  • Christopher Lohse

    PhD Thesis, ongoing

  • Raphael Franke

    PhD Thesis, ongoing

  • Simon Bing

    Phd - Postdoctoral Supervision, ongoing

  • Sirisha Sandadi

    Master's Thesis, ongoing

  • Ruoxuan Liu

    Binding Affinity Prediction with Deep Learning: Structural Learning or Dataset Bias?

    Master's Thesis, 2026

  • Pascal Schumann

    Learning Continuous Dosage Strategies for Sepsis via Offline Reinforcement Learning

    Master's Thesis, 2026

  • Johannes Isle

    Learning Causal Graphs via Discrete, Order Based Search: The FLOP Algorithm

    Bachelor's Thesis, 2026

  • Nicolas-Domenic Reiter

    Structural equation processes - A linear model for causal inference in discrete-time

    Phd - Postdoctoral Supervision, 2025

  • Hannah Westhoff

    Free probability, (*q*, *t*)-deformed processes, and applications

    Master's Thesis, 2022

  • Matthias Valvekens

    Representation theory for non-extremal subfactors and their standard invariants

    Master's Thesis, 2016