Obserwuj
Carlo Lucibello
Carlo Lucibello
Assistant Professor, Bocconi University
Zweryfikowany adres z unibocconi.it
Tytuł
Cytowane przez
Cytowane przez
Rok
Unreasonable effectiveness of learning neural networks: From accessible states and robust ensembles to basic algorithmic schemes
C Baldassi, C Borgs, JT Chayes, A Ingrosso, C Lucibello, L Saglietti, ...
Proceedings of the National Academy of Sciences 113 (48), E7655-E7662, 2016
1872016
Subdominant dense clusters allow for simple learning and high computational performance in neural networks with discrete synapses
C Baldassi, A Ingrosso, C Lucibello, L Saglietti, R Zecchina
Physical review letters 115 (12), 128101, 2015
1472015
A Scaling Hypothesis for the Euclidean Bipartite Matching Problem
S Caracciolo, C Lucibello, G Parisi, G Sicuro
Phys. Rev. E 90, 012118, 2014
822014
Local entropy as a measure for sampling solutions in constraint satisfaction problems
C Baldassi, A Ingrosso, C Lucibello, L Saglietti, R Zecchina
Journal of Statistical Mechanics: Theory and Experiment 2016 (2), 023301, 2016
592016
Learning may need only a few bits of synaptic precision
C Baldassi, F Gerace, C Lucibello, L Saglietti, R Zecchina
Physical Review E 93 (5), 052313, 2016
322016
Entropic gradient descent algorithms and wide flat minima
F Pittorino, C Lucibello, C Feinauer, G Perugini, C Baldassi, ...
Journal of Statistical Mechanics: Theory and Experiment 2021 (12), 124015, 2021
282021
Finite size corrections to disordered Ising models on Random Regular Graphs
C Lucibello, F Morone, G Parisi, F Ricci-Tersenghi, T Rizzo
Phys. Rev. E 90, 012146, 2014
282014
Finite-size corrections to disordered systems on Erdös-Rényi random graphs
U Ferrari, C Lucibello, F Morone, G Parisi, F Ricci-Tersenghi, T Rizzo
Physical Review B 88 (18), 184201, 2013
282013
Role of synaptic stochasticity in training low-precision neural networks
C Baldassi, F Gerace, HJ Kappen, C Lucibello, L Saglietti, E Tartaglione, ...
Physical review letters 120 (26), 268103, 2018
262018
Loop expansion around the Bethe approximation through the M-layer construction
A Altieri, MC Angelini, C Lucibello, G Parisi, F Ricci-Tersenghi, T Rizzo
Journal of Statistical Mechanics: Theory and Experiment 2017 (11), 113303, 2017
242017
One-loop diagrams in the random Euclidean matching problem
C Lucibello, G Parisi, G Sicuro
Physical Review E 95 (1), 012302, 2017
172017
Clustering of solutions in the symmetric binary perceptron
C Baldassi, R Della Vecchia, C Lucibello, R Zecchina
Journal of Statistical Mechanics: Theory and Experiment 2020 (7), 073303, 2020
152020
Unexpected upper critical dimension for spin glass models in a field predicted by the loop expansion around the bethe solution at zero temperature
MC Angelini, C Lucibello, G Parisi, G Perrupato, F Ricci-Tersenghi, ...
Physical Review Letters 128 (7), 075702, 2022
142022
The statistical mechanics of random set packing and a generalization of the Karp-Sipser algorithm
C Lucibello, F Ricci-Tersenghi
International Journal of Statistical Mechanics 2014, 1-13, 2014
132014
Deep learning via message passing algorithms based on belief propagation
C Lucibello, F Pittorino, G Perugini, R Zecchina
Machine Learning: Science and Technology 3 (3), 035005, 2022
112022
Exponential Capacity of Dense Associative Memories
C Lucibello, M Mézard
Physical Review Letters 132 (7), 077301, 2024
102024
Loop expansion around the Bethe solution for the random magnetic field Ising ferromagnets at zero temperature
MC Angelini, C Lucibello, G Parisi, F Ricci-Tersenghi, T Rizzo
Proceedings of the National Academy of Sciences 117 (5), 2268-2274, 2020
102020
Generalized approximate survey propagation for high-dimensional estimation
C Lucibello, L Saglietti, Y Lu
International Conference on Machine Learning, 4173-4182, 2019
102019
Storage and learning phase transitions in the random-features hopfield model
M Negri, C Lauditi, G Perugini, C Lucibello, E Malatesta
Physical Review Letters 131 (25), 257301, 2023
6*2023
Neural networks: from the perceptron to deep nets
M Gabrié, S Ganguli, C Lucibello, R Zecchina
arXiv preprint arXiv:2304.06636, 2023
62023
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–20