
Alexander Marx
Postdoc Fellow
I am a Postdoc Fellow affiliated with the ETH AI Center and the Medical Data Science group at ETH Zürich. My research focuses on causality, information theory, and representation learning to approach modern challenges in the medical and biological domain. I obtained my Master’s degree in Bioinformatics in 2016 and completed my PhD in Computer Science in 2021 at Saarland University. During my PhD, I was part of the Exploratory Data Analysis group affiliated with the CISPA Helmholtz Center for Information Security and the Max Planck Institute for Informatics.
For Students: If you are looking for a thesis/semester project, feel free to contact me. Currently, my main focus is on representation learning from multimodal or time series data, which may include applications to the medical domain [1,2], and causality—especially considering heteroscedastic noise in causal models [3,4].
News
- (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.
- (Dec 2022) Our ICLR'23 workshop proposal on Time Series Representation Learning for Health (TSRL4H) got accepted.
- (Oct 2022) New preprint titled "On the Identifiability and Estimation of Causal Location-Scale Noise Models" is available.
- (Aug 2022) I gave a tutorial at the Machine Learning Summer School in Healthcare and Biosciences.
- (May 2022) Our paper titled "Inferring Cause and Effect in the Presence of Heteroscedastic Noise" got accepted at ICML'22.
- (Apr 2022) A portrait article about me and my research got featured in ETH news.
- (Feb 2022) I received an AISTATS'22 Reviewer Award (awarded to top 10% best reviewers).
- (Dec 2021) Our paper titled "Estimating Mutual Information via Geodesic kNN") got accepted at SDM'22.
- (Dec 2021) Two papers (one, two) were accepted the AAAI-22 Workshop ITCI'22.
- (Dec 2021) I will co-teach the course AI Center Projects in Machine Learning Research in the upcoming summer semester.
- (Sep 2021) I started as a Post-Doc Fellow at the ETH AI Center.
Activities
Reviewing for Conferences & Journals
- Reviewer for the International Conference on Machine Learning (ICML'22)
- Reviewer for the International Conference on Artificial Intelligence and Statistics (AISTATS'21,22 [Top 10% Reviewer Award],23[Top 10% Reviewer Award])
- 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)
- 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
- 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
On the Identifiability and Estimation of Causal Location-Scale Noise Models
Alexander Immer, Christoph Schultheiss, Julia E. Vogt, Bernhard Schölkopf, Peter Bühlmann, Alexander Marx
arXiv, 2022 Oct
Inferring Cause and Effect in the Presence of Heteroscedastic Noise
Sascha Xu, Osman Mian, Alexander Marx, Jilles Vreeken
Proceedings of the International Conference on Machine Learning, PMLR, 2022 Jul
Estimating Mutual Information via Geodesic kNN
Alexander Marx, Jonas Fischer
Proceedings of the SIAM International Conference on Data Mining, SIAM, 2022 Apr
Formally Justifying MDL-based Inference of Cause and Effect
Alexander Marx, Jilles Vreeken
Proceedings of the AAAI Workshop on Information Theoretic Causal Inference and Discovery, 2022 Mar
Causal Inference with Heteroscedastic Noise Models
Sascha Xu, Alexander Marx, Osman Mian, Jilles Vreeken
Proceedings of the AAAI Workshop on Information Theoretic Causal Inference and Discovery, 2022 Mar
View all