Alexander Marx
Professor
I am a professor at TU Dortmund, leading the Causality group at the Research Center for Trustworthy Data Science and Security and the Department of Statistics, and a member of the ELLIS society. My research is at the intersection of causality and machine learning, focusing on causal discovery, causal representation learning, information theory, and Bayesian deep learning. Prior to my current position, I was a Postdoctoral Researcher Computational Biology Group at ETH Zürich, a Postdoc-Fellow at the ETH AI Center and part of the Medical Data Science Group. I did my PhD in the Exploratory Data Analysis group affiliated with the CISPA Helmholtz Center for Information Security and the Max Planck Institute for Informatics.
Job Advertisement
I am actively searching for PhD students and research assistants. Feel free to reach out! More details are provided here.
Thesis Projects
There are several open projects suitable for a Master's or Bachelor's thesis in topic areas such as causal discovery, (Bayesian) image regression, and mutual information estimation.
News
- (Sep 2024) I gave a talk in the AIMS Lecture Series in Essen.
- (Aug 2024) Our paper "Predicting Risk for Nocturnal Hypoglycemia after Physical Activity in Children with Type 1 Diabetes" got accepted at Frontiers in Medicine
- (Jun 2024) I gave a talk at the DoDaS Colloquium in Dortmund.
- (Jun 2024) I started as a professor in Causality at TU Dortmund.
- (Feb 2024) I became a member of the ELLIS society.
- (Feb 2024) Accepted poster at RECOMB on "Gene-level Inference of Regulatory effects As Factorization of Function of Expressions" or short GIRAFFE.
- (Jan 2024) Or submission "Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning" has been accepted to ICLR'24.
- (Jan 2024) I joined the Computational Biology Group led by Niko Beerenwinkel!
- (Nov 2023) Our work "Blood Glucose Forecasting from Temporal and Static Information in Children with T1D" has been accepted for publication at Frontiers in Pediatrics.
- (Nov 2023) Selected to be among the top reviewers at NeurIPS'23.
- (Oct 2023) New preprint "The Mixtures and the Neural Critics: On the Pointwise Mutual Information Profiles of Fine Distributions" is available!
- (Sep 2023) Two papers got accepted to NeurIPS'23: 1) "Beyond Normal: On the Evaluation of Mutual Information Estimators", and 2) "Effective Bayesian Heteroscedastic Regression with Deep Neural Networks".
- (Apr 2023) Our paper "On the Identifiability and Estimation of Causal Location-Scale Noise Models" got accepted to ICML'23.
- (Mar 2023) Our paper "3DIdentBox: A Toolbox for Identifiability Benchmarking" got accapted to the dataset track at CLeaR'23
- (Feb 2023) I received an AISTATS'23 Reviewer Award (awarded to top 10% best reviewers).
- (Jan 2023) Our submission "Identifiability Results for Multimodal Contrastive Learning" got accepted to ICLR'23.
For more updates access the news arxiv.
Activities
Reviewing for Conferences & Journals
- Reviewer for the Conference on Neural Information Processing Systems (NeurIPS'23 [Top 10% Reviewer Award],24)
- Reviewer for the International Conference on Machine Learning (ICML'22,23,24)
- Reviewer for the International Conference on Artificial Intelligence and Statistics (AISTATS'21,22 [Top 10% Reviewer Award],23[Top 10% Reviewer Award],24, 25)
- PC Member for the SIAM International Conference on Data Mining (SDM'21)
- PC Member for the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD'21)
- Reviewer for the Machine Learning for Health Symposium (ML4H'22,23)
- Reviewed for the journal Data Mining and Knowledge Discovery (DAMI'22)
- Reviewed for the journal IEEE Access in 2020
- Reviewer for the IEEE International Symposium on Information Theory (ISIT'19,20)
- PC Member for the workshops AAAI-ITCI'22 and NeurIPS-TS4H
Invited Talks
- AIMS Lecture Series, Institute for Artificial Intelligence in Medicine, Essen, 2024
- DoDaS Colloquium, Center for Data Science & Simulation, TU Dortmund, 2024
- Neuro-Mechanistic Modeling group, DFKI Saarbrücken, 2023
- Faculty of Business and Economics, University of Lausanne, 2023
- Statistical Colloquium, TU Dortmund, 2023
- Tutorial at Machine Learning Summer School in Healthcare and Biosciences, 2022
- Data Mining reading group, TU Eindhoven (virtual), 2020
- CWI Machine Learning Seminar, CWI Amsterdam, 2019
- Explanatory Data Analysis group, Leiden University, 2019
Publications
Predicting Risk for Nocturnal Hypoglycemia after Physical Activity in Children with Type 1 Diabetes
Heike Leutheuser, Marc Bartholet, Alexander Marx, Marc Pfister, Marie-Anne Burckhardt, Sara Bachmann, Julia E Vogt
Frontiers in Medicine, vol. 11, Frontiers, 2024
Anomaly Detection by Context Contrasting
Alain Ryser, Thomas M Sutter, Alexander Marx, Julia E Vogt
arXiv preprint arXiv:2405.18848, 2024
Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning
Mirco Mutti, Riccardo De Santi, Marcello Restelli, Alexander Marx, Giorgia Ramponi
ICLR, 2024 May
Blood Glucose Forecasting from Temporal and Static Information in Children with T1D
Alexander Marx, Francesco Di Stefano, Heike Leutheuse, Kieran Chin-Cheong, Marc Pfister, Marie-Anne Burckhardt, Sara Bachmann Brenner, Julia E. Vogt
Frontiers in Pediatrics, vol. 11, 2023
Effective Bayesian Heteroscedastic Regression with Deep Neural Networks
Alexander Immer, Emanuele Palumbo, Alexander Marx*, Julia E Vogt*
NeurIPS, 2023 Dec
View all