Biography
I’m a full professor at Saarland University since 2026 and I’m also part of the Amsterdam Machine Learning Lab at the University Amsterdam. I’m an ELLIS Scholar in the Interactive Learning and Interventional Representations program. During Spring 2022, I was visiting the Simons Institute at UC Berkeley for a semester on Causality. During Spring 2026, I visited the Isaac Newton Institute at the University of Cambridge for the programme Causal inference: From theory to practice and back again.
Important: I don’t have any open position at the moment, and once I will have them, I will advertise them widely, so no need to email me.
My research is at the intersection of causality and machine learning. My goal is to find how can causal reasoning improve state-of-the-art AI, especially in terms of robustness, generalization across domains/tasks, and safety, and imbue it with the strong theoretical guarantees typical of causality research. This Figure summarizes the research directions I have been pursuing and how they connect to each other.
My research focuses on three directions: (i) causal representation learning (i.e. learning causal variables from high-dimensional data, e.g. sequences of images [1, 2, 3, 4]), (i) causal discovery (i.e. learning causal relations from data, e.g. focusing on a statistically and computationally efficient way [5]), and (iii) downstream tasks, e.g., how can causality ideas help ML/RL adapt to new domains or nonstationarity and compositionally generalize ([6, 7, 8]).
Previously I was a Research Scientist at MIT-IBM Watson AI lab and a postdoctoral researcher at IBM Research NY, working on methods to design experiments that would allow one to learn causal relations in a sample-efficient and intervention-efficient way. I received a PhD at VU Amsterdam on learning causal relations jointly from different experimental settings, even with latent confounders and small samples. During my PhD, I interned at Google Zürich and NYC. Previously, I studied Computer Engineering at Politecnico di Milano and Torino and at the University of Trieste.
Download my resumé .
- Causal Representation Learning
- Causal discovery
- Causality-inspired ML and RL
- Causality in general
- Neurosymbolic/StarAI approaches
PhD in Artificial Intelligence, 2017
VU Amsterdam
MSc in Computer Engineering, 2011
Politecnico di Milano, Politecnico di Torino (double degree)
BSc in Computer Engineering, 2008
Università degli Studi di Trieste
Team
PhD students
Danru Xu
PhD student (UvA)
Mátyás Schubert
PhD student (UvA)
Nadja Rutsch
PhD student (AUMC)
Roel Hulsman
PhD student (UvA)
Thomas Wessels
PhD student (Utrecht University)
Yi Han
PhD student (UvA)
Close collaborators
Fan Feng
PhD student (City University Hong Kong)
Riccardo Massidda
ELLIS PhD student (University of Pisa/UvA)
Guest researchers
Alessandro Trenta
Visiting PhD student (U Pisa)
Jacopo Dapueto
Visiting PhD student (U Genoa)
Alumni
Andrea Conte
Master student (University of Torino)
Angelos Nalmpantis
Master student (UvA)
Aoqi Zuo
Visiting PhD student (University of Melbourne)
Daan Roos
PhD student (UvA)
Danilo de Goede
Master student (UvA)
Davide Talon
Visiting PhD student (IIT Genoa)
Eva Sevenster
Master student (UvA)
Frank Brongers
Master student (UvA)
Ilze Amanda Auzina
PhD student at University of Amsterdam
Jakub Řeha
PhD student (UvA)
Macha Meijer
Master student (UvA)
Mara Pislar
Master student (UvA)
Phillip Lippe
ELLIS PhD student (UvA/Qualcomm)
Pieter Bouwman
Master student (UvA)
Theofanis Aslanidis
Master student (UvA)
Willemijn de Hoop
Master student (UvA)
Yohan Runhaar
Master student (UvA, Adyen)
Yongtuo Liu
PhD student (University of Amsterdam)
News
1 March 2026: I have started as a full professor in Machine Learning at Saarland University, but I will also keep working part-time as a professor at the University of Amsterdam, where I will start my VIDI project.
January 2026- March 2026: I will be visiting the Isaac Newton Institute in Cambridge for the programme Causal inference: From theory to practice and back again. Excited to give a talk in the Foundations of Causal Inference workshop with so many excellent researchers!
December 2025: UAI 2026 will be in Amsterdam! I will be general chair with Silvia Chiappa, and will also organizing locally with Ana Mićković
November 2025: My VIDI project CANES: a CAusal NEuro-Symbolic approach to integrating perception and abstract reasoning was accepted! I will be hiring 2 PhDs and 1 postdoc in Spring 2026, stay tuned!
20 October 2025: I gave a lecture on Causality and RL at the SIKS course on RL for Adaptive Hybrid Intelligence that attracted PhD students from all across the Netherlands.
15 October 2025: I had an amazing time in Warsaw for ML in PL, where I gave an invited talk on CRL!
July 2025: Silvia Chiappa and I successfully organized UAI 2025 in Rio as program chairs with a fantastic organization committee!
May 2025: Matyas went to present our work on SNAP: Sequential Non-Ancestor Pruning at AISTATS 2025.
April 2025: Organized a causality workshop with Virginia Aglietti at DALI 2025 in Sorrento.
February 2025: My first two PhD students got their PhD, both cum laude! Congrats [Riccardo Massidda (U Pisa)] (https://bsky.app/profile/smaglia.bsky.social/post/3lifjpfg2ek2w) and Phillip Lippe (U Amsterdam)!! Matyas and I attended the Bellairs workshop on Causality in the Era of Foundation Models.
December 2024: Guido Imbens (Stanford) visited our group.
October 2024: Visiting Harvard to give an invited talk on (i)CITRIS and BISCUIT in the Harvard Data Science Initiative Causal Seminar. I’m also a communication chair for CLeaR 2025 and helping organize a CRL workshop at NeurIPS 2024.
September 2024: I have been travelling quite a lot, first to Dagstuhl for a seminar on Artificial Intelligence and Formal Methods Join Forces for Reliable Autonomy , then to Nijmegen to give a keynote at PGM 2024, Oslo as an examiner for the PhD defense of Ghadi Al Hajj (it was successful :), and finally to Münich for an Oktoberfest Causality mini-workshop organized by TUM.
Summer 2024: Busy summer! First I co-organized a Logic and AI workshop at the Institute for Advanced Study (IAS) here in Amsterdam. Then I went to UAI 2024, where Riccardo presented our UAI 2024 paper on learning linear abstractions, even without knowing neither the abstract nor the concrete causal graph. There I gave an invited talk at the Causal Inference for Time Series workshop and then helped organize the (other?) Causal Inference workshop. After that I attended ICML 2024, where Danru and I presented our ICML 2024 paper on CRL in partially observed settings, while with Yongtuo we presented our ICML 2024 paper on Amortized Equation Discovery in Hybrid Dynamical Systems. Finally, I gave an invited talk at ONRL for their AI Seminar Series.
Contact and Jobs
For teaching matters, please do not use the email and contact me via the platform used during the course.
Important. Before emailing me about positions, please check the details below. Due to the high frequency of emails, I will not be able to answer to questions that are already covered here.
PhD students. I currently do not have any open position. When I will have some, I will advertise them widely, so no need to email me.
Postdocs. I will also have an open postdoc position for 2 years at UvA for my VIDI project CANES on learning concepts with theoretical guarantee. The deadline will probably be in late 2026 - stay tuned!
Inters and other jobs. I currently don’t have open positions for interns or research assistants.
Bachelor/Master students. I currently don’t take any Bachelor or Master students at Saarland University until the next academic year. I don’t supervise Bachelor or Master students from other universities.
- s DOT magliacane AT uva DOT nl
- Lab 42, Science Park 900, Amsterdam, 1012 WX