Matteo Vilucchio
PhD Student in Machine Learning and Statistical Physics at EPFL.
About Me
I’m a PhD student at EPFL working at the intersection of high-dimensional statistics, computer science, and statistical physics. I study robust and adversarial learning in high dimensions and work on making statistical-physics methods rigorous; I was also an intern at G-Research.
I am lucky to be mentored by Florent Krzakala and to share the lab with all the other IdePHICS memebers.
Outside of my research I spend most of my time climbing either small rocks, medium walls or big mountains. I also enjoy reading and listening to music.
Research Interests
- Mathematical Physics
- Adversarial and Robust Learning
- Statistical Learning Theory
- High Dimensional Statistics
Latest Updates
Since today, I am in Taipei for the Physics of Learning semester meeting, where I will present recent advances in the Neural Lofi framework.
I will attend the Princeton Summer School 2026, and I will be on the US East Coast and available for meetings.
Our paper On the existence of consistent adversarial attacks in high-dimensional linear classification has been accepted as a Spotlight at ICML 2026.