Follow
Carlo Baldassi
Title
Cited by
Cited by
Year
Entropy-sgd: Biasing gradient descent into wide valleys
P Chaudhari, A Choromanska, S Soatto, Y LeCun, C Baldassi, C Borgs, ...
Journal of Statistical Mechanics: Theory and Experiment 2019 (12), 124018, 2019
7732019
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
1882016
Fast and accurate multivariate Gaussian modeling of protein families: predicting residue contacts and protein-interaction partners
C Baldassi, M Zamparo, C Feinauer, A Procaccini, R Zecchina, M Weigt, ...
PloS one 9 (3), e92721, 2014
1752014
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
1482015
Simultaneous identification of specifically interacting paralogs and interprotein contacts by direct coupling analysis
T Gueudré, C Baldassi, M Zamparo, M Weigt, A Pagnani
Proceedings of the National Academy of Sciences 113 (43), 12186-12191, 2016
1272016
Efficient supervised learning in networks with binary synapses
C Baldassi, A Braunstein, N Brunel, R Zecchina
Proceedings of the National Academy of Sciences 104 (26), 11079 -11084, 2007
1192007
Shape similarity, better than semantic membership, accounts for the structure of visual object representations in a population of monkey inferotemporal neurons
C Baldassi, A Alemi-Neissi, M Pagan, JJ DiCarlo, R Zecchina, D Zoccolan
PLoS computational biology 9 (8), e1003167, 2013
1172013
Shaping the learning landscape in neural networks around wide flat minima
C Baldassi, F Pittorino, R Zecchina
Proceedings of the National Academy of Sciences 117 (1), 161-170, 2020
772020
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
602016
Efficiency of quantum vs. classical annealing in nonconvex learning problems
C Baldassi, R Zecchina
Proceedings of the National Academy of Sciences 115 (7), 1457-1462, 2018
592018
Properties of the geometry of solutions and capacity of multilayer neural networks with rectified linear unit activations
C Baldassi, EM Malatesta, R Zecchina
Physical review letters 123 (17), 170602, 2019
532019
RNAs competing for microRNAs mutually influence their fluctuations in a highly non-linear microRNA-dependent manner in single cells
C Bosia, F Sgrò, L Conti, C Baldassi, D Brusa, F Cavallo, FD Cunto, ...
Genome biology 18, 1-14, 2017
432017
A behavioral characterization of the drift diffusion model and its multialternative extension for choice under time pressure
C Baldassi, S Cerreia-Vioglio, F Maccheroni, M Marinacci, M Pirazzini
Management Science 66 (11), 5075-5093, 2020
422020
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
312021
Unveiling the structure of wide flat minima in neural networks
C Baldassi, C Lauditi, EM Malatesta, G Perugini, R Zecchina
Physical Review Letters 127 (27), 278301, 2021
292021
Learning through atypical "phase transitions" in overparameterized neural networks
C Baldassi, C Lauditi, EM Malatesta, R Pacelli, G Perugini, R Zecchina
Physical Review E 106 (1), 014116, 2022
282022
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
Parle: parallelizing stochastic gradient descent
P Chaudhari, C Baldassi, R Zecchina, S Soatto, A Talwalkar, A Oberman
arXiv preprint arXiv:1707.00424, 2017
252017
A three-threshold learning rule approaches the maximal capacity of recurrent neural networks
A Alemi, C Baldassi, N Brunel, R Zecchina
PLoS computational biology 11 (8), e1004439, 2015
242015
The system can't perform the operation now. Try again later.
Articles 1–20