Bruno Loureiro

I am a CNRS researcher in the DATA team, part of the Centre for Data Science at the École Normale Supérieure in Paris. My work lies at the intersection of machine learning and statistical mechanics. I also serve as a Professeur Attaché at Université Paris Sciences et Lettres (PSL), where I teach in both undergraduate and graduate programs across its affiliated institutions.

If you are interested in my research, you can find a complete list of my publications here.

news

Aug 01, 2025	My project MAPLE (Mathematical Analysis of Pattern Learning and Extraction) has been selected for the ANR JCJC 2025!!! I am actively looking for strong and motivated postdocs to work on the theory of feature learning starting from September 2025. More info here.
Feb 28, 2025	I am slowly writing a set of lecture notes for a course on the “Mathematics of Deep Learning” I teach at the MASH/IASD M2 programs, with some of my favourite topics. It is still a draft, but you can check them here!
Feb 04, 2025	In our recent pre-print on “Optimal Spectral Transitions in High-Dimensional Multi-Index Models” we propose a spectral method and show that it achieves the optimal weak-recovery threshold for multi-index models among first order methods, a result proven in our previous work.
Jan 22, 2025	Our papers: A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities (Oral) Fundamental computational limits of weak learnability in high-dimensional multi-index models A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-Offs were accepted at AISTATS 2025. See you in Thailand in May!
Nov 03, 2024	Our paper How two-layer neural networks learn, one (giant) step at a time was accepted for publication at JMLR! It will also feature as a poster at ICLR in the JMLR track.