Francesco Camilli

According to our database, Francesco Camilli authored at least 11 papers between 2022 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of three.

2025

Statistical mechanics of extensive-width Bayesian neural networks near interpolation.

Jean Barbier, Francesco Camilli, Minh-Toan Nguyen, Mauro Pastore, Rudy Skerk

CoRR, May, 2025

Optimal generalisation and learning transition in extensive-width shallow neural networks near interpolation.

Jean Barbier, Francesco Camilli, Minh-Toan Nguyen, Mauro Pastore, Rudy Skerk

CoRR, January, 2025

Information-theoretic reduction of deep neural networks to linear models in the overparametrized proportional regime.

Francesco Camilli, Daria Tieplova, Eleonora Bergamin, Jean Barbier

Proceedings of the Thirty Eighth Annual Conference on Learning Theory, 2025

2024

The Onset of Parisi's Complexity in a Mismatched Inference Problem.

Francesco Camilli, Pierluigi Contucci, Emanuele Mingione

Entropy, January, 2024

On the phase diagram of extensive-rank symmetric matrix denoising beyond rotational invariance.

Jean Barbier, Francesco Camilli, Justin Ko, Koki Okajima

CoRR, 2024

Information limits and Thouless-Anderson-Palmer equations for spiked matrix models with structured noise.

Jean Barbier, Francesco Camilli, Marco Mondelli, Yizhou Xu

CoRR, 2024

2023

The Decimation Scheme for Symmetric Matrix Factorization.

Francesco Camilli, Marc Mézard

CoRR, 2023

Fundamental limits of overparametrized shallow neural networks for supervised learning.

Francesco Camilli, Daria Tieplova, Jean Barbier

CoRR, 2023

Central limit theorem for the overlaps on the Nishimori line.

Francesco Camilli, Pierluigi Contucci, Emanuele Mingione

CoRR, 2023

2022

Matrix factorization with neural networks.

Francesco Camilli, Marc Mézard

CoRR, 2022

Bayes-optimal limits in structured PCA, and how to reach them.

Jean Barbier, Francesco Camilli, Marco Mondelli, Manuel Sáenz

CoRR, 2022