Timeline

I spent two weeks at the Benasque Science Center for the XI edition of “Partial Differential Equations, Optimization, Numerics, and Machine Learning” (August 23 – September 4, 2026), where I gave three talks and co-chaired the thematic session “PDEs and Machine Learning” together with Aidan Chaumet. Here are the slides, in case you’re interested in these topics: Hybrid Generative Modeling for Neuroscience (August 25) — whole-brain dynamics and the fitting problem, joint work with L. Liverani, E. Zuazua and X. Kobeleva. Link Data-Driven Control in Infinite-Dimensional Spaces (August 27) — informativity and persistency of excitation, with applications to data-driven controllability and LQR. Link Neural ODEs: A Representer Theorem (September 1) — joint work with Zhengping Ji. Link The full program is available on the conference website. ...

I gave a talk at our internal machine learning seminar, together with Max Golightly, on the road that leads from optimal control to reinforcement learning. We started from the deterministic picture — variational calculus, Hamilton–Jacobi, the Pontryagin maximum principle — and then moved to the probabilistic one, going through Markov decision processes, dynamic programming and policy gradient methods. I’m sharing the slides here in case you’re interested in these topics Link. ...

This week I had the chance to present at the workshop “The Mathematics of Scientific Machine Learning and Digital Twins” in Palermo, Italy. My talk focused on the intersection between kernel methods and machine learning. I’m sharing the slides here in case you’re interested in these topics Link.