Francesco Camilli

Postdoctoral Fellows
Postdoctoral Fellow
Profile image
Quantitative Life Sciences
+39 040 2240 147
fcamilli@ictp.it
+39 040 2240 147
fcamilli@ictp.it
SISSA-217
https://sites.google.com/view/francesco-camilli
0000-0001-6530-0707

Francesco Camilli


I was born in Pesaro, a peaceful city on the Adriatic coast of Italy. There I started moving my first steps in Physics and Mathematics at the Liceo Scientifico G. Marconi, where I got my high school diploma.

Then I moved to Bologna to study Physics in the oldest university of the world in continuous operation! During my Bachelor and Master studies, I was also a member of the Collegio Superiore, an institute of excellence of the University of Bologna.

I have completed my PhD in Mathematics and Physics in a joint program between the University of Bologna and the École normale supérieure of Paris under the extraordinary supervision of professors P. Contucci and M. Mézard.

I am currently a postdoctoral fellow at the International Centre for Theoretical Pysics (ICTP) of Trieste.

Publications

Preprint
2024
On the phase diagram of extensive-rank symmetric matrix denoising beyond rotational invariance
Jean Barbier | Francesco Camilli | Justin Ko | Koki Okajima
Preprint
2024
Information limits and Thouless-Anderson-Palmer equations for spiked matrix models with structured noise
Jean Barbier | Francesco Camilli | Marco Mondelli | Yizhou Xu
Preprint
2024
Information limits and Thouless-Anderson-Palmer equations for spiked matrix models with structured noise
Jean Barbier | Francesco Camilli | Marco Mondelli | Yizhou Xu
Journal article
2024
The decimation scheme for symmetric matrix factorization
Francesco Camilli
Journal article
2023
Matrix factorization with neural networks
Francesco Camilli
Preprint
2023
The Decimation Scheme for Symmetric Matrix Factorization
Francesco Camilli | Marc Mézard
Book
2023
Lezioni di meccanica elementare e oltre
Francesco Camilli
Preprint
2023
Fundamental limits of overparametrized shallow neural networks for supervised learning
Francesco Camilli | Daria Tieplova | Jean Barbier
Preprint
2023
Central limit theorem for the overlaps on the Nishimori line
Francesco Camilli | Pierluigi Contucci | Emanuele Mingione
Journal article
2023
The Onset of Parisi’s Complexity in a Mismatched Inference Problem
Entropy (2023)
Francesco Camilli | Pierluigi Contucci | EMANUELE MINGIONE
Journal article
2023
Fundamental limits in structured principal component analysis and how to reach them
Francesco Camilli
Preprint
2022
Matrix factorization with neural networks
Francesco Camilli | Marc Mézard
Journal article
2022
An inference problem in a mismatched setting: a spin-glass model with Mattis interaction
SciPost Physics (2022)
Francesco Camilli
Preprint
2022
Bayes-optimal limits in structured PCA, and how to reach them
Jean Barbier | Francesco Camilli | Marco Mondelli | Manuel Saenz
Journal article
2021
The Multi-species Mean-Field Spin-Glass on the Nishimori Line
Journal of Statistical Physics (2021)
Francesco Camilli
Preprint
2021
An inference problem in a mismatched setting: a spin-glass model with Mattis interaction
Francesco Camilli | Pierluigi Contucci | Emanuele Mingione
Journal article
2021
A Statistical Physics approach to a multi-channel Wigner spiked model
Europhysics Letters (2021)
Diego Alberici | Francesco Camilli | Pierluigi Contucci | Emanuele Mingione
Journal article
2021
The Solution of the Deep Boltzmann Machine on the Nishimori Line
Communications in Mathematical Physics (2021)
Diego Alberici | Francesco Camilli | Pierluigi Contucci | Emanuele Mingione
Preprint
2020
The solution of the deep Boltzmann machine on the Nishimori line
Diego Alberici | Francesco Camilli | Pierluigi Contucci | Emanuele Mingione
Preprint
2020
The multi-species mean-field spin-glass on the Nishimori line
Diego Alberici | Francesco Camilli | Pierluigi Contucci | Emanuele Mingione

Sorry no results

ROccella Conference on INference and AI - ROCKIN' AI 2024

This multidisciplinary conference seeks to unite leading researchers from the fields of statistical physics, mathematical physics, and machine learning. Our goal is to offer diverse perspectives on crucial topics in contemporary machine learning, including:

…