Seguir
Francesco Cagnetta
Francesco Cagnetta
Collaborateur scientifique, École polytechnique fédérale de Lausanne (EPFL)
Dirección de correo verificada de epfl.ch
Título
Citado por
Citado por
Año
Large fluctuations and dynamic phase transition in a system of self-propelled particles
F Cagnetta, F Corberi, G Gonnella, A Suma
Physical review letters 119 (15), 158002, 2017
772017
Active growth and pattern formation in membrane-protein systems
F Cagnetta, MR Evans, D Marenduzzo
Physical review letters 120 (25), 258001, 2018
212018
Work fluctuations of self-propelled particles in the phase separated state
P Chiarantoni, F Cagnetta, F Corberi, G Gonnella, A Suma
Journal of Physics A: Mathematical and Theoretical 53 (36), 36LT02, 2020
192020
Locality defeats the curse of dimensionality in convolutional teacher-student scenarios
A Favero, F Cagnetta, M Wyart
Advances in Neural Information Processing Systems 34, 9456-9467, 2021
182021
Efficiency of one-dimensional active transport conditioned on motility
F Cagnetta, E Mallmin
Physical Review E 101 (2), 022130, 2020
162020
Learning sparse features can lead to overfitting in neural networks
L Petrini, F Cagnetta, E Vanden-Eijnden, M Wyart
Advances in Neural Information Processing Systems 35, 9403-9416, 2022
112022
What can be learnt with wide convolutional neural networks?
F Cagnetta, A Favero, M Wyart
International Conference on Machine Learning, 2023, 2022
102022
Strong anomalous diffusion of the phase of a chaotic pendulum
F Cagnetta, G Gonnella, A Mossa, S Ruffo
Europhysics Letters 111 (1), 10002, 2015
102015
Kinetic roughening in active interfaces
F Cagnetta, MR Evans, D Marenduzzo
EPJ Web of Conferences 230, 00001, 2020
92020
Statistical mechanics of a single active slider on a fluctuating interface
F Cagnetta, MR Evans, D Marenduzzo
Physical Review E 99 (4), 042124, 2019
82019
Universal properties of active membranes
F Cagnetta, V Škultéty, MR Evans, D Marenduzzo
Physical Review E 105 (1), L012604, 2022
72022
How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model
F Cagnetta, L Petrini, UM Tomasini, A Favero, M Wyart
arXiv preprint arXiv:2307.02129, 2023
5*2023
Nonequilibrium Strategy for Fast Target Search on the Genome
F Cagnetta, D Michieletto, D Marenduzzo
Physical Review Letters 124 (19), 198101, 2020
4*2020
How deep convolutional neural networks lose spatial information with training
UM Tomasini, L Petrini, F Cagnetta, M Wyart
Machine Learning: Science and Technology 4 (4), 045026, 2023
32023
Renormalization group study of the dynamics of active membranes: Universality classes and scaling laws
F Cagnetta, V Škultéty, MR Evans, D Marenduzzo
Physical Review E 105 (1), 014610, 2022
22022
Work fluctuations in the active Ornstein–Uhlenbeck particle model
M Semeraro, A Suma, I Petrelli, F Cagnetta, G Gonnella
Journal of Statistical Mechanics: Theory and Experiment 2021 (12), 123202, 2021
22021
Inviscid limit of the active interface equations
F Cagnetta, MR Evans
Journal of Statistical Mechanics: Theory and Experiment 2019 (11), 113206, 2019
22019
Active interfaces, a universal approach
F Cagnetta
The University of Edinburgh, 2020
12020
Kernels, Data & Physics
F Cagnetta, D Oliveira, M Sabanayagam, N Tsilivis, J Kempe
arXiv preprint arXiv:2307.02693, 2023
2023
Feature learning and overfitting in neural networks
F Cagnetta
Bulletin of the American Physical Society, 2023
2023
El sistema no puede realizar la operación en estos momentos. Inténtalo de nuevo más tarde.
Artículos 1–20