Research Group Mathias Drton
Mathias Drton
Prof. Dr.
Principal Investigator
Mathias Drton
is Professor of Mathematical Statistics at TU Munich.
He works on methods and theory in the field of statistics. His main interest is the analysis of complex multivariate data. The main focus lies on graphical models, which capture fine causal relationships and find manifold applications in modern data-driven science. The aim of the research is, amongst others, to clarify by means of algebraic and probability theory under which circumstances data allow conclusions about causal relationships and to develop efficient methods for their estimation.
Team members @MCML
PhD Students
Hanke Guo
→ Group Mathias Drton
Mathematical Statistics
David Strieder
→ Group Mathias Drton
Mathematical Statistics
Nils Sturma
→ Group Mathias Drton
Mathematical Statistics
Daniele Tramontano
→ Group Mathias Drton
Mathematical Statistics
Recent News @MCML
Publications @MCML
2025
[30]
S. Lumpp • M. Drton
On weak convergence of Gaussian conditional distributions.
Statistics and Probability Letters 226.110497. Nov. 2025. DOI
On weak convergence of Gaussian conditional distributions.
Statistics and Probability Letters 226.110497. Nov. 2025. DOI
[29]
Y. S. Wang • M. Kolar • M. Drton
Confidence Sets for Causal Orderings.
Journal of the American Statistical Association. Oct. 2025. DOI
Confidence Sets for Causal Orderings.
Journal of the American Statistical Association. Oct. 2025. DOI
[28]
D. Strieder • M. Drton
Identifying total causal effects in linear models under partial homoscedasticity.
International Journal of Approximate Reasoning 183.109455. Aug. 2025. DOI
Identifying total causal effects in linear models under partial homoscedasticity.
International Journal of Approximate Reasoning 183.109455. Aug. 2025. DOI
[27]
R. Schwank • M. Drton
On the distance between mean and geometric median in high dimensions.
Preprint (Aug. 2025). arXiv
On the distance between mean and geometric median in high dimensions.
Preprint (Aug. 2025). arXiv
[26]
M. Drton • M. Garrote-López • N. Nikov • E. Robeva • Y. S. Wang
Causal Discovery for Linear Non-Gaussian Models with Disjoint Cycles.
UAI 2025 - 41st Conference on Uncertainty in Artificial Intelligence. Rio de Janeiro, Brazil, Jul 21-25, 2025. URL GitHub
Causal Discovery for Linear Non-Gaussian Models with Disjoint Cycles.
UAI 2025 - 41st Conference on Uncertainty in Artificial Intelligence. Rio de Janeiro, Brazil, Jul 21-25, 2025. URL GitHub
[25]
D. Tramontano • Y. Kivva • S. Salehkaleybar • N. Kiyavash • M. Drton
Causal Effect Identification in lvLiNGAM from Higher-Order Cumulants.
ICML 2025 - 42nd International Conference on Machine Learning. Vancouver, Canada, Jul 13-19, 2025. URL
Causal Effect Identification in lvLiNGAM from Higher-Order Cumulants.
ICML 2025 - 42nd International Conference on Machine Learning. Vancouver, Canada, Jul 13-19, 2025. URL
[24]
L. Hafner • G. Sturm • S. Lumpp • M. Drton • M. List
Single-cell differential expression analysis between conditions within nested settings.
Briefings in Bioinformatics 26.4. Jul. 2025. DOI
Single-cell differential expression analysis between conditions within nested settings.
Briefings in Bioinformatics 26.4. Jul. 2025. DOI
[23]
N. Sturma • M. Drton
Trek-Based Parameter Identification for Linear Causal Models With Arbitrarily Structured Latent Variables.
Preprint (Jul. 2025). arXiv
Trek-Based Parameter Identification for Linear Causal Models With Arbitrarily Structured Latent Variables.
Preprint (Jul. 2025). arXiv
[22]
T. Boege • M. Drton • B. Hollering • S. Lumpp • P. Misra • D. Schkoda
Conditional independence in stationary distributions of diffusions.
Stochastic Processes and their Applications 184.104604. Jun. 2025. DOI
Conditional independence in stationary distributions of diffusions.
Stochastic Processes and their Applications 184.104604. Jun. 2025. DOI
[21]
K. Göbler • T. Windisch • M. Drton
Nonlinear Causal Discovery for Grouped Data.
Preprint (Jun. 2025). arXiv
Nonlinear Causal Discovery for Grouped Data.
Preprint (Jun. 2025). arXiv
[20]
[19]
[18]
M. Drton • A. Grosdos • I. Portakal • N. Sturma
Algebraic Sparse Factor Analysis.
SIAM Journal on Applied Algebra and Geometry 9. Feb. 2025. DOI
Algebraic Sparse Factor Analysis.
SIAM Journal on Applied Algebra and Geometry 9. Feb. 2025. DOI
[17]
E. Banzato • M. Drton • K. Saraf-Poor • H. Shi
Existence of Direct Density Ratio Estimators.
Preprint (Feb. 2025). arXiv
Existence of Direct Density Ratio Estimators.
Preprint (Feb. 2025). arXiv
[16]
N. Sturma • M. Kranzlmueller • I. Portakal • M. Drton
Matching Criterion for Identifiability in Sparse Factor Analysis.
Preprint (Feb. 2025). arXiv
Matching Criterion for Identifiability in Sparse Factor Analysis.
Preprint (Feb. 2025). arXiv
[15]
2024
[14]
Y. Liang • O. Zadorozhnyi • M. Drton
Kernel-Based Differentiable Learning of Non-Parametric Directed Acyclic Graphical Models.
PGM 2024 - 12th International Conference on Probabilistic Graphical Models. Nijmegen, The Netherlands, Sep 11-13, 2024. URL
Kernel-Based Differentiable Learning of Non-Parametric Directed Acyclic Graphical Models.
PGM 2024 - 12th International Conference on Probabilistic Graphical Models. Nijmegen, The Netherlands, Sep 11-13, 2024. URL
[13]
D. Strieder • M. Drton
Identifying Total Causal Effects in Linear Models under Partial Homoscedasticity.
PGM 2024 - 12th International Conference on Probabilistic Graphical Models. Nijmegen, The Netherlands, Sep 11-13, 2024. URL
Identifying Total Causal Effects in Linear Models under Partial Homoscedasticity.
PGM 2024 - 12th International Conference on Probabilistic Graphical Models. Nijmegen, The Netherlands, Sep 11-13, 2024. URL
[12]
D. Schkoda • E. Robeva • M. Drton
Causal Discovery of Linear Non-Gaussian Causal Models with Unobserved Confounding.
Preprint (Aug. 2024). arXiv
Causal Discovery of Linear Non-Gaussian Causal Models with Unobserved Confounding.
Preprint (Aug. 2024). arXiv
[11]
D. Tramontano • Y. Kivva • S. Salehkaleybar • M. Drton • N. Kiyavash
Causal Effect Identification in LiNGAM Models with Latent Confounders.
ICML 2024 - 41st International Conference on Machine Learning. Vienna, Austria, Jul 21-27, 2024. URL
Causal Effect Identification in LiNGAM Models with Latent Confounders.
ICML 2024 - 41st International Conference on Machine Learning. Vienna, Austria, Jul 21-27, 2024. URL
[10]
K. Göbler • M. Drton • S. Mukherjee • A. Miloschewski
High-dimensional undirected graphical models for arbitrary mixed data.
Electronic Journal of Statistics 18.1. Jun. 2024. DOI
High-dimensional undirected graphical models for arbitrary mixed data.
Electronic Journal of Statistics 18.1. Jun. 2024. DOI
[9]
P. Dettling • M. Drton • M. Kolar
On the Lasso for Graphical Continuous Lyapunov Models.
CLeaR 2024 - 3rd Conference on Causal Learning and Reasoning. Los Angeles, CA, USA, Apr 01-03, 2024. URL
On the Lasso for Graphical Continuous Lyapunov Models.
CLeaR 2024 - 3rd Conference on Causal Learning and Reasoning. Los Angeles, CA, USA, Apr 01-03, 2024. URL
[8]
K. Göbler • T. Windisch • M. Drton • T. Pychynski • M. Roth • S. Sonntag
causalAssembly: Generating Realistic Production Data for Benchmarking Causal Discovery.
CLeaR 2024 - 3rd Conference on Causal Learning and Reasoning. Los Angeles, CA, USA, Apr 01-03, 2024. URL
causalAssembly: Generating Realistic Production Data for Benchmarking Causal Discovery.
CLeaR 2024 - 3rd Conference on Causal Learning and Reasoning. Los Angeles, CA, USA, Apr 01-03, 2024. URL
[7]
D. Strieder • M. Drton
Dual Likelihood for Causal Inference under Structure Uncertainty.
CLeaR 2024 - 3rd Conference on Causal Learning and Reasoning. Los Angeles, CA, USA, Apr 01-03, 2024. URL
Dual Likelihood for Causal Inference under Structure Uncertainty.
CLeaR 2024 - 3rd Conference on Causal Learning and Reasoning. Los Angeles, CA, USA, Apr 01-03, 2024. URL
[6]
N. Sturma • M. Drton • D. Leung
Testing many constraints in possibly irregular models using incomplete U-statistics.
Journal of the Royal Statistical Society. Series B (Statistical Methodology) 86.4. Mar. 2024. DOI
Testing many constraints in possibly irregular models using incomplete U-statistics.
Journal of the Royal Statistical Society. Series B (Statistical Methodology) 86.4. Mar. 2024. DOI
2023
[5]
N. Sturma • C. Squires • M. Drton • C. Uhler
Unpaired Multi-Domain Causal Representation Learning.
NeurIPS 2023 - 37th Conference on Neural Information Processing Systems. New Orleans, LA, USA, Dec 10-16, 2023. URL
Unpaired Multi-Domain Causal Representation Learning.
NeurIPS 2023 - 37th Conference on Neural Information Processing Systems. New Orleans, LA, USA, Dec 10-16, 2023. URL
[4]
D. Strieder • M. Drton
Confidence in causal inference under structure uncertainty in linear causal models with equal variances.
Journal of Causal Inference 11.1. Dec. 2023. DOI
Confidence in causal inference under structure uncertainty in linear causal models with equal variances.
Journal of Causal Inference 11.1. Dec. 2023. DOI
[3]
G. Keropyan • D. Strieder • M. Drton
Rank-Based Causal Discovery for Post-Nonlinear Models.
AISTATS 2023 - 26th International Conference on Artificial Intelligence and Statistics. Valencia, Spain, Apr 25-27, 2023. URL
Rank-Based Causal Discovery for Post-Nonlinear Models.
AISTATS 2023 - 26th International Conference on Artificial Intelligence and Statistics. Valencia, Spain, Apr 25-27, 2023. URL
2022
[2]
R. Foygel Barber • M. Drton • N. Sturma • L. Weihs
Half-trek criterion for identifiability of latent variable models.
Annals of Statistics 50.6. Dec. 2022. DOI
Half-trek criterion for identifiability of latent variable models.
Annals of Statistics 50.6. Dec. 2022. DOI
[1]
D. Strieder • M. Drton
On the choice of the splitting ratio for the split likelihood ratio test.
Electronic Journal of Statistics 16.2. Mar. 2022. DOI
On the choice of the splitting ratio for the split likelihood ratio test.
Electronic Journal of Statistics 16.2. Mar. 2022. DOI
©all images: LMU | TUM