I’m a 2nd year Ph.D. student in Operations Research and Financial Engineering (ORFE) at Princeton University.
My work lies at the intersection of probabilistic machine learning and non-convex optimization.
I am fortunate to be advised by prof. Boris Hanin.
Before my Ph.D. I obtained a Master degree in Mathematics (track Stochastics and Data Science) from University of Turin and I was a Senior Allievo at Collegio Carlo Alberto.
I used to have a strong focus on Probability Theory and my research has deepened Bayesian neural networks and their infinite-width prior and posterior limits. I was fortunate to work with prof. Stefano Favaro and prof. Dario Trevisan.
I got my Bachelor in Mathematics (track Computational Math) from University of Pisa, with a thesis on universality of neural networks.
News
- Jul. 2025: Attending COLT 2025 (Lyon) to present a poster at the TASC Workshop.
- Jun. 2025: Working on stability and implicit bias of GD/SGD and designing principled noise, clipping, and step-size schedules for reliable training.
Publications / Preprints
- F. Caporali, S. Favaro, D. Trevisan, Student-$t$ processes as infinite-width limits of posterior Bayesian NNs, In: TASC workshop, COLT 2025
Teaching
- Tutorial Instructor, Probability and Statistics, B.Sc. Mathematics for Finance and Insurance (Mar. 2023 - June 2023).
- Teaching Assistant, Probability Theory (ORF526) (Sep. 2025 - Dec. 2025).