Scholar
Måns Magnusson
Google Scholar ID: 6AA-AAcAAAAJ
Department of Statistics, Uppsala University, Sweden
Citations & Impact
Citations
1,864
H-index
16
i10-index
21
Publications
20
Co-authors
41
list available
Publications
Resume (English only)
Academic Achievements
- PhD thesis 'Scalable and Efficient Probabilistic Topic Model Inference for Textual Data' awarded the Cramér Prize for best dissertation in Statistics and Mathematical Statistics in Sweden (2018)
- Received 'Statistician of the Year' award in 2023 for work on Botten Ada, a Bayesian model for Swedish election prediction
- Elected member of the Swedish Young Academy in May 2023 (five-year term)
- Elected member of the European Laboratory for Learning and Intelligent Systems (ELLIS) in 2024
- Principal investigator of a Swedish Research Council (SRC) starting grant in data science on 'Improving Probabilistic Programming generalizability'
Research Experience
- Currently Associate Professor in Statistics at Uppsala University
- Postdoc (2018–2020) under Aki Vehtari at the Department of Computer Science, Aalto University, Finland
- Guest researcher/PhD student at Cornell University under David Mimno during doctoral studies
- Previously worked as a statistician at the Swedish Agency for Education, Swedish Agency for Crime Prevention, and Swedish Agency for Public Health
- Project member of two large SRC grants: 'Mining for Meaning' and 'Welfare State Analytics', focusing on large-scale text analysis in sociology and history
- Co-PI of the SWERIK research infrastructure project funded by Riksbankens jubileumsfond
- Awarded Uppsala University AI4Research sabbatical grant in 2024 for AI applications in research
Background
- Associate Professor in Statistics at Uppsala University, Sweden
- Primary research interests: Bayesian inference, probabilistic machine learning, and statistical inference from textual data
- Affiliated with the Institute for Analytical Sociology at Linköping University and the Institute for Future Studies
- Research focuses on Bayesian statistics and probabilistic machine learning, especially model evaluation, diagnostics, and inference algorithms
- Works on textual data analysis with applications in sociology, political science, and law, including transformer-based neural networks and probabilistic latent semantic models (e.g., word embeddings, topic models)
- Addresses challenges in efficiently curating large-scale textual data
