Stefano Spigler
Cited by
Cited by
Scaling description of generalization with number of parameters in deep learning
M Geiger, A Jacot, S Spigler, F Gabriel, L Sagun, S d’Ascoli, G Biroli, ...
Journal of Statistical Mechanics: Theory and Experiment 2020 (2), 023401, 2020
A jamming transition from under-to over-parametrization affects generalization in deep learning
S Spigler, M Geiger, S d’Ascoli, L Sagun, G Biroli, M Wyart
Journal of Physics A: Mathematical and Theoretical 52 (47), 474001, 2019
Jamming transition as a paradigm to understand the loss landscape of deep neural networks
M Geiger, S Spigler, S d'Ascoli, L Sagun, M Baity-Jesi, G Biroli, M Wyart
Physical Review E 100 (1), 012115, 2019
Comparing dynamics: Deep neural networks versus glassy systems
M Baity-Jesi, L Sagun, M Geiger, S Spigler, GB Arous, C Cammarota, ...
International Conference on Machine Learning, 314-323, 2018
Disentangling feature and lazy learning in deep neural networks: an empirical study.
M Geiger, S Spigler, A Jacot, M Wyart
Mean-field avalanches in jammed spheres
S Franz, S Spigler
Physical Review E 95 (2), 022139, 2017
Asymptotic learning curves of kernel methods: empirical data versus teacher–student paradigm
S Spigler, M Geiger, M Wyart
Journal of Statistical Mechanics: Theory and Experiment 2020 (12), 124001, 2020
Proceedings of the 35th International Conference on Machine Learning
M Baity-Jesi, L Sagun, M Geiger, S Spigler, GB Arous, C Cammarota, ...
PMLR, 2018
How isotropic kernels perform on simple invariants
J Paccolat, S Spigler, M Wyart
Machine Learning: Science and Technology 2 (2), 025020, 2021
Random-diluted triangular plaquette model: Study of phase transitions in a kinetically constrained model
S Franz, G Gradenigo, S Spigler
Physical Review E 93 (3), 032601, 2016
Les avalanches dans les systèmes vitreux
S Spigler
Université Paris sciences et lettres, 2017
Avalanches in glassy system
S Spigler
Université Paris Sud, Université Paris Saclay, 2017
Plaquette models for glasses
S Spigler
The system can't perform the operation now. Try again later.
Articles 1–13