I am an assistant professor in the Amsterdam Machine Learning Lab at the University Amsterdam and an ELLIS Scholar in the Interactive Learning and Interventional Representations program. During Spring 2022, I was visiting the Simons Institute in Berkeley for a semester on Causality.

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 varaibles 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 .