Scholar
Sebastian Weichwald
Google Scholar ID: lApaQd4AAAAJ
University of Copenhagen / formerly Max Planck Institute for Intelligent Systems, ETH Zurich
Citations & Impact
Citations
1,119
H-index
13
i10-index
14
Publications
20
Co-authors
36
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Published multiple papers on causal model transformations and abstractions (UAI 2017 & 2021). Argued that common interpretation of actions as interventions renders causal model predictions circular and thus non-falsifiable (2025). Made the case for time in causal graphs (2025). Revealed how common causal discovery benchmarks may be gamed and fail to capture meaningful progress (NeurIPS 2021 & 2023). Developed 'gadjid' for evaluating learned causal graphs (UAI 2024) and 'CIfly' for fast algorithm development in graphical causal inference (2025). Succeeded in the NeurIPS Causality 4 Climate competition (PMLR 2020).
Research Experience
- Currently a faculty member in the Department of Mathematical Sciences at the University of Copenhagen, part of the Copenhagen Causality Lab (CoCaLa), and co-lead for causality at the Pioneer Centre for AI (P1). Participated in and succeeded in the NeurIPS Causality 4 Climate competition. Developed 'gadjid' for evaluating learned causal graphs via adjustment identification distances and 'CIfly' for fast algorithm development in graphical causal inference.
Education
- PhD: ETH Zurich and Max Planck Institute for Intelligent Systems; Postdoc: University of Copenhagen
Background
- Research interests include the foundations of causal modeling and its practical applications. Aims to understand and resolve what holds causal modeling back in practice by clarifying its foundations (specifying what is being modeled, how it can be tested, which metrics reflect progress) and by prioritizing ready-to-use implementations. Works with a relentlessly curious group and inspiring collaborators.
Miscellany
- Serves on the fellowship evaluation committee of the Danish Data Science Academy (DDSA).
