activity
20172019
most citedActivated Aging Dynamics and Effective Trap Model Description in the Random Energy Model

29 citations · 29 across the 1 of their papers we have counts for

collaborators

5 papers

cond-mat.dis-nn2019

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…

cond-mat.dis-nn2018

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…

cond-mat.dis-nn2018

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…

stat.ML2018

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 (…

cond-mat.dis-nn201729 cited

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…