Rosalba Pacelli

According to our database, Rosalba Pacelli authored at least 5 papers between 2021 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Kernel Shape Renormalization In Bayesian Shallow Networks: a Gaussian Process Perspective.

Rosalba Pacelli, Lorenzo Giambagli, Paolo Baglioni

Proceedings of the IEEE Workshop on Complexity in Engineering, 2024

2023

A statistical mechanics framework for Bayesian deep neural networks beyond the infinite-width limit.

Rosalba Pacelli, Sebastiano Ariosto, Mauro Pastore, Francesco Ginelli, Marco Gherardi, Pietro Rotondo

Nat. Mac. Intell., December, 2023

Les Houches Lectures on Deep Learning at Large & Infinite Width.

Yasaman Bahri, Boris Hanin, Antonin Brossollet, Vittorio Erba, Christian Keup, Rosalba Pacelli, James B. Simon

CoRR, 2023

Local Kernel Renormalization as a mechanism for feature learning in overparametrized Convolutional Neural Networks.

Riccardo Aiudi, Rosalba Pacelli, Alessandro Vezzani, Raffaella Burioni, Pietro Rotondo

CoRR, 2023

2021

Learning through atypical "phase transitions" in overparameterized neural networks.

Carlo Baldassi, Clarissa Lauditi, Enrico M. Malatesta, Rosalba Pacelli, Gabriele Perugini, Riccardo Zecchina

CoRR, 2021