About
Hi! I’m an incoming tenure-track Assistant Professor in Applied Mathematics at École Polytechnique, starting in February 2027. My research focuses on machine learning for structured data, with emphasis on time series, spatiotemporal data, and graph processing.
I am currently spending the final months of my Swiss National Science Foundation fellowship at Mila and McGill University, hosted by Prof. Reihaneh Rabbany.
I am a proud member of the ELLIS Society.
Short bio
Before Mila and McGill, I was an SNSF postdoc at EPFL with Prof. Olga Fink and previously at the University of Oxford with Prof. Michael Bronstein. I obtained my PhD from USI under the supervision of Prof. Cesare Alippi, with a thesis on graph deep learning methods for time series forecasting. I have been a visiting researcher at Imperial College London with Prof. Danilo Mandic and previously got my MSc and BSc in Computer Science and Engineering at Politecnico di Milano.
I am also affiliated with IDSIA, at USI, and the NGMLG, at the UiT the Arctic University of Norway.
My research has been published in top-tier machine learning venues, including JMLR, NeurIPS, ICML, and ICLR, where I also frequently serve as a reviewer. My work on graph-based forecasting has received the Informatics Europe Best Dissertation Award 2025. I am one of the creators of Torch Spatiotemporal.
News
All news →-
Very happy to share that I will be joining École Polytechnique as a tenure-track Assistant Professor in Applied Mathematics in February 2027!
-
New preprint on continual graph multi-agent reinforcement learning is out!
-
I moved to Mila and McGill University to spend the final months of my SNSF project working with Prof. Reihaneh Rabbany.
-
Why do time series models need long context windows? Our paper has been accepted at NeurIPS 2026!
-
I’ll be giving lectures on graph neural networks to the doctoral candidates of the ASSESS MSCA doctoral network at their training event at TU Dresden.