Since 2019, I am a PhD candidate at the Institute for Theoretical Computer Science in Lübeck doing research in causal inference. The focus of my work is on developing efficient algorithms for problems in causal graphical modelling by combining graph theory, algorithmics and complexity theory.
I studied Computer Science at the University of Lübeck from 2013 to 2019.
I have been involed in competitive programming and in particular the ICPC contests since 2015, first as participant and now as coach for the teams from Uni Lübeck as well as a regular jury member in German ICPC contests (such the Wintercontest and the GCPC).
Together with Moritz Schauer and Martin Keller, I am one of the authors of the CausalInference Julia package. It provides efficient implementations of causal structure learning algorithms such as PC and GES as well as methods for finding adjustment sets in DAGs.
Recently, I had some fun programming a multiplayer word game as an open source web application in Elixir using the Phoenix Framework . You can play the game here and find the source code on GitHub .
My CV is available here (English) and here (German).
Awards
- Best Master Award 2018/2019 (University of Lübeck)
- Distinguished Paper Award at AAAI 2021
- Best Student Paper Award at UAI 2021
- Best Student Paper Award at UAI 2022
- Top Reviewer at UAI 2022
- AI Newcomer 2023 (awarded by the German Informatics Society)
Invited Talks and Workshops
- 13.04.2022: ‘Algorithms for Causal Inference’ at the Darmstädter Ontologenkreis
- 13.03.2023: 'Algorithms for Markov Equivalent DAGs' (Poster) at the Young European Statisticians Series on Causal Inference
- 03.05.2023: ‘A New Constructive Criterion for Markov Equivalence of MAGs’ at the Causal Discussion Group
- 14.06.2023: ‘Linear-Time Algorithms for Front-Door Adjustment in Causal Graphs’ at the TUM Seminar on Statistics and Data Science
Full List of Publications (including Preprints)
Causal structure learning with momentum: Sampling distributions over Markov Equivalence Classes of DAGs
M. Schauer, M. Wienöbst
Linear-Time Algorithms for Front-Door Adjustment in Causal Graphs
M. Wienöbst, B. van der Zander, M. Liśkiewicz (AAAI 2024)
Polynomial-Time Algorithms for Counting and Sampling Markov Equivalent DAGs with Applications
M. Wienöbst, M. Bannach, M. Liśkiewicz (JMLR 24(213), 2023)
Practical Algorithms for Orientations of Partially Directed Graphical Models
M. Luttermann*, M. Wienöbst*, M. Liśkiewicz (CLeaR 2023: *Equal Contribution)
Efficient Enumeration of Markov Equivalent DAGs
M. Wienöbst, M. Luttermann, M. Bannach, M. Liśkiewicz (AAAI 2023: Oral)
Identification in Tree-shaped Linear Structural Causal Models
B. van der Zander, M. Wienöbst, M. Bläser, M. Liskiewicz (AISTATS 2022)
A New Constructive Criterion for Markov Equivalence of MAGs
M. Wienöbst, M. Bannach, M. Liśkiewicz (UAI 2022: Oral + Best Student Paper)
An Approach to Reduce the Number of Conditional Independence Tests in the PC Algorithm
M. Wienöbst, M. Liśkiewicz (KI 2021)
Extendability of Causal Graphical Models: Algorithms and Computational Complexity
M. Wienöbst, M. Bannach, M. Liśkiewicz (UAI 2021: Long Talk + Best Student Paper)
Polynomial-Time Algorithms for Counting and Sampling Markov Equivalent DAGs
M. Wienöbst, M. Bannach, M. Liśkiewicz (AAAI 2021: Distinguished Paper)
PACE Solver Description: PID*
M. Bannach, S. Berndt, M. Schuster, M. Wienöbst (IPEC 2020)
PACE Solver Description: Fluid
M. Bannach, S. Berndt, M. Schuster, M. Wienöbst (IPEC 2020)
Recovering Causal Structures from Low-Order Conditional Independencies
M. Wienöbst, M. Liśkiewicz (AAAI 2020)