I am an assistant professor in the Amsterdam Machine Learning Lab at the University Amsterdam. During Spring 2022, I was visiting the Simons Institute in Berkeley for a semester on Causality.
The goal of my research is to find how can causality improve current machine learning (ML) algorithms, especially in terms of robustness, generalization across domains/tasks, and safety. My research focuses on three directions: causal representation learning (i.e. learning causal factors from high-dimensional data, e.g. sequences of images [1, 2, 3]), causal discovery (i.e. learning causal relations from data), and causality-inspired ML, e.g. how can ideas from causality help ML/RL adapt to new domains, nonstationarity and varying number of objects with different latent parameters, even when we cannot guarantee that we identified the true causal factors.
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 .
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
Summer 2024: Busy summer! First I will be co-organizing a ``Logic and AI’’ workshop at the Institute for Advanced Study (IAS) here in Amsterdam. Then I will go to UAI 2024, where Riccardo will be presenting our UAI 2024 paper on learning linear abstractions, even without knowing neither the abstract nor the concrete causal graph. There I will give an invited talk at the Causal Inference for Time Series workshop and then help organize the (other?) Causal Inference workshop. After that I will attend ICML 2024, where Danru and I will present our ICML 2024 paper on CRL in partially observed settings, while with Yongtuo we will present our ICML 2024 paper on Amortized Equation Discovery in Hybrid Dynamical Systems.
June 2024: Invited talk at the CVPR 2024 Causal and Object-centric Representation Learning for Robotics workshop. It was a surprisingly sunny week in Seattle!
April 2024: ICLR 2024 - I was one of the volunteer chairs, and we presented our work with our collaborators in ISTA, MILA, ETH and ServiceNow on multi-view causal representation learning as an ICLR Spotlight.
April 2024: Davide had an oral talk at CLeaR 2024 on our paper about reusability and compositionality of causal representations.
February 2024: Danru, Phillip and I participated in the Bellairs Causality workshop presenting our works on causal representation learning in partially observed settings and in temporal sequences with actions.
February 2024: Matyas and I participated in the Causal Discovery workshop in Bremen, presenting our ongoing work on ``Scalable targeted causal discovery: motivation and preliminary results`.
December 2023: NeurIPS 2023 - we had 2 conference papers: Modulated Neural ODEs and DAFT-RL, we organized the NeurIPS 2023 workshop on Causal Representation Learning and had 4 workshop posters.
October 2023: Invited talk at the IROS workshop on Causality for Robotics: Answering the Question of Why!
September 2023: Invited talk at the 5th Conference of the Central European Network in the session on Causal discovery with a view on the life sciences the Biozentrum in Basel, CH.
August 2023: Keynote on Causality-inspired ML at the ELLIS Doctoral Symposium 2023 in Helsinki. Here are the slides
August 2023: I helped organize UAI 2023 as online chair. We also organized a Causality in time series workshop.
July 2023: Invited talk in the Second Workshop on Spurious Correlations at ICML.
July 2023: Invited talk on Causality-inspired ML at the European Meeting of Statisticians in Warsaw. Pierogi <3
June 2023: Invited talk on Causal vs Causality-inspired representation learning at the IST seminar series Mathematics, Physics & Machine Learning.
June 2023: Lecture at the SIKS causal inference course on constraint-based causal discovery.
For teaching matters, you can contact me via Canvas.
PhD students If you have questions about joining my group or AMLab, check this list first.
Other jobs Currently I don’t have any open vacancy for interns, research assistants or postdocs, but if I do, they will be announced on the UvA vacancies website.
Master students If you are a Master in AI student at the University of Amsterdam and are interested in causality, feel free to contact me for potential thesis topics. As a rule, I also don’t supervise Bachelor or Master students from other universities.