29 citations · 29 across the 1 of their papers we have counts for
5 papers
Maximum-energy records in glassy energy landscapes
Ivailo Hartarsky, Marco Baity-Jesi, Riccardo Ravasio +2
We study the evolution of the maximum energy $E_\max(t)$ reached between time and time in the dynamics of simple models with glassy energy landscapes, in instant quenches f…
The jamming transition as a paradigm to understand the loss landscape of deep neural networks
Mario Geiger, Stefano Spigler, Stéphane d'Ascoli +4
Deep learning has been immensely successful at a variety of tasks, ranging from classification to AI. Learning corresponds to fitting training data, which is implemented by descend…
Activated dynamics: an intermediate model between REM and p-spin
Marco Baity-Jesi, Alexandre Achard-de Lustrac, Giulio Biroli
In order to study the activated dynamics of mean-field glasses, which takes place on times of order exp(N), where N is the system size, we introduce a new model, the Correlated Ran…
Comparing Dynamics: Deep Neural Networks versus Glassy Systems
M. Baity-Jesi, L. Sagun, M. Geiger +6
We analyze numerically the training dynamics of deep neural networks (DNN) by using methods developed in statistical physics of glassy systems. The two main issues we address are (…
Activated Aging Dynamics and Effective Trap Model Description in the Random Energy Model
Marco Baity-Jesi, Giulio Biroli, Chiara Cammarota
We study the out-of-equilibrium aging dynamics of the Random Energy Model (REM) ruled by a single spin-flip Metropolis dynamics. We focus on the dynamical evolution taking place on…