2.1k citations · 16.3k across the 193 of their papers we have counts for
11 papers · 1 filter
Properties of equilibria and glassy phases of the random Lotka-Volterra model with demographic noise
Ada Altieri, Felix Roy, Chiara Cammarota +1
In this letter we study a reference model in theoretical ecology, the disordered Lotka-Volterra model for ecological communities, in the presence of finite demographic noise. Our t…
Out of equilibrium Phase Diagram of the Quantum Random Energy Model
Giulio Biroli, Davide Facoetti, Marco Schiró +2
In this paper we study the out-of-equilibrium phase diagram of the quantum version of Derrida's Random Energy Model, which is the simplest model of mean-field spin glasses. We inte…
An analytic theory of shallow networks dynamics for hinge loss classification
Franco Pellegrini, Giulio Biroli
Neural networks have been shown to perform incredibly well in classification tasks over structured high-dimensional datasets. However, the learning dynamics of such networks is sti…
Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval
Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota +3
Despite the widespread use of gradient-based algorithms for optimizing high-dimensional non-convex functions, understanding their ability of finding good minima instead of being tr…
Glasses and aging: A Statistical Mechanics Perspective
Francesco Arceri, François P. Landes, Ludovic Berthier +1
We review the field of the glass transition, glassy dynamics and aging from a statistical mechanics perspective. We give a brief introduction to the subject and explain the main ph…
Dynamical Instantons and Activated Processes in Mean-Field Glass Models
V. Ros, G. Biroli, C. Cammarota
We focus on the energy landscape of a simple mean-field model of glasses and analyze activated barrier-crossing by combining the Kac-Rice method for high-dimensional Gaussian lands…
Triple descent and the two kinds of overfitting: Where & why do they appear?
Stéphane d'Ascoli, Levent Sagun, Giulio Biroli
A recent line of research has highlighted the existence of a "double descent" phenomenon in deep learning, whereby increasing the number of training examples causes the general…
Dynamical Mean-Field Theory and Aging Dynamics
Ada Altieri, Giulio Biroli, Chiara Cammarota
Dynamical Mean-Field Theory (DMFT) replaces the many-body dynamical problem with one for a single degree of freedom in a thermal bath whose features are determined self-consistentl…
Double Trouble in Double Descent : Bias and Variance(s) in the Lazy Regime
Stéphane d'Ascoli, Maria Refinetti, Giulio Biroli +1
Deep neural networks can achieve remarkable generalization performances while interpolating the training data perfectly. Rather than the U-curve emblematic of the bias-variance tra…
Anomalous dynamics in the ergodic side of the Many-Body Localization transition and the glassy phase of Directed Polymers in Random Media
Giulio Biroli, Marco Tarzia
Using the non-interacting Anderson tight-binding model on the Bethe lattice as a toy model for the many-body quantum dynamics, we propose a novel and transparent theoretical explan…
Interplay between percolation and glassiness in the random Lorentz gas
Giulio Biroli, Patrick Charbonneau, Eric I. Corwin +4
The random Lorentz gas (RLG) is a minimal model of transport in heterogeneous media. It also models the dynamics of a tracer in a glassy system. These two perspectives, however, ar…