Luca Pesce

Hi! I am a final-year PhD student at École Polytechnique Fédérale de Lausanne (EPFL) advised by Florent Krzakala.

My research investigates the theoretical foundations of modern deep learning systems to understand why they are so effective in practice. I explore how general-purpose training methods (e.g., SGD) exploit low-dimensional latent structures in high-dimensional data, leveraging tools from statistical physics and high-dimensional statistics.

Previously, I worked as a research intern at Aqemia and I took part in an International Msc program in Theoretical Physics organized by: ICTP, Paris Cité, Politecnico di Torino, SISSA, Sorbonne, and Paris Saclay.

If you want to know more about my research, the list of my publications is here.