Scholar
Matteo Vilucchio
Google Scholar ID: lu9hh14AAAAJ
PhD Student, EPFL
Citations & Impact
Citations
15
H-index
3
i10-index
0
Publications
6
Co-authors
6
list available
Publications
Resume (English only)
Academic Achievements
- Will present work titled “A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-offs” at AISTAT2025; attending the Winter School “Towards a theory for typical-case algorithmic hardness” in Les Houches, France; attending the Statistical Physics of Deep Learning school in Como, Italy, and presenting the same work during the poster session.
Research Experience
- Working at EPFL on the intersection of High Dimensional Statistics, Computer Science, and Statistical Physics.
Education
- PhD Student in Machine Learning and Statistical Physics at EPFL, mentored by Florent Krzakala, and part of the IdePHICS team.
Background
- Research interests include Mathematical Physics, Adversarial and Robust Learning, Statistical Learning Theory, and High Dimensional Statistics. His research focuses on understanding the properties of adversarial/robust estimators in high-dimensional cases and making non-rigorous but surprisingly effective methods of statistical physics rigorous to expand the toolbox for studying high-dimensional problems.
Miscellany
- Outside of research, he spends most of his time climbing (small rocks, medium walls, or big mountains), enjoys reading, and listening to music.
