BALDASSI, CARLO
BALDASSI, CARLO
Dipartimento Scienza Applicata e Tecnologia
023017
Learning through atypical phase transitions in overparameterized neural networks
2022 Baldassi, C.; Lauditi, C.; Malatesta, E. M.; Pacelli, R.; Perugini, G.; Zecchina, R.
Wide flat minima and optimal generalization in classifying high-dimensional Gaussian mixtures
2020 Baldassi, Carlo; Malatesta, Enrico M; Negri, Matteo; Zecchina, Riccardo
From inverse problems to learning: A Statistical Mechanics approach
2018 Baldassi, Carlo; Gerace, Federica; Saglietti, Luca; Zecchina, Riccardo
Role of Synaptic Stochasticity in Training Low-Precision Neural Networks
2018 Baldassi, Carlo; Federica, Gerace; Kappen, Hilbert J.; Lucibello, Carlo; Luca, Saglietti; Tartaglione, Enzo; Zecchina, Riccardo
A method to reduce the rejection rate in Monte Carlo Markov chains
2017 Baldassi, Carlo
RNAs competing for microRNAs mutually influence their fluctuations in a highly non-linear microRNA-dependent manner in single cells
2017 Bosia, Carla; Sgrò, Francesco; Conti, Laura; Baldassi, Carlo; Cavallo, Federica; Di Cunto, Ferdinando; Turco, Emilia; Pagnani, Andrea; Zecchina, Riccardo
Learning may need only a few bits of synaptic precision
2016 Baldassi, Carlo; Gerace, Federica; Lucibello, Carlo; Saglietti, Luca; Zecchina, Riccardo
Local entropy as a measure for sampling solutions in constraint satisfaction problems
2016 Baldassi, Carlo; Ingrosso, Alessandro; Lucibello, Carlo; Saglietti, Luca; Zecchina, Riccardo
Simultaneous identification of specifically interacting paralogs and interprotein contacts by direct coupling analysis
2016 Gueudre, Thomas; Baldassi, Carlo; Zamparo, Marco; Weigt, Martin; Pagnani, Andrea
Unreasonable effectiveness of learning neural networks: From accessible states and robust ensembles to basic algorithmic schemes
2016 Baldassi, Carlo; Borgs, Christian; Chayes, Jennifer T; Ingrosso, Alessandro; Lucibello, Carlo; Saglietti, Luca; Zecchina, Riccardo
A Max-Sum algorithm for training discrete neural networks
2015 Baldassi, Carlo; Braunstein, Alfredo
A Three-Threshold Learning Rule Approaches the Maximal Capacity of Recurrent Neural Networks
2015 Alemi, Alireza; Baldassi, Carlo; Brunel, Nicolas; Zecchina, Riccardo
Subdominant Dense Clusters Allow for Simple Learning and High Computational Performance in Neural Networks with Discrete Synapses
2015 Baldassi, Carlo; Ingrosso, Alessandro; Lucibello, Carlo; Saglietti, Luca; Zecchina, Riccardo
Fast and Accurate Multivariate Gaussian Modeling of Protein Families: Predicting Residue Contacts and Protein-Interaction Partners
2014 Baldassi, Carlo; Zamparo, Marco; Feinauer, Christoph; Procaccini, A.; Zecchina, Riccardo; Weigt, R.; Pagnani, Andrea
Shape similarity, better than semantic membership, accounts for the structure of visual object representations in a population of monkey inferotemporal neurons
2013 Baldassi, Carlo; Alemi Neissi, A.; Pagan, M.; Dicarlo, J.; Zecchina, Riccardo; Zoccolan, D.
Theory and learning protocols for the material tempotron model
2013 Baldassi, Carlo; Braunstein, Alfredo; Zecchina, Riccardo
Generalization Learning in a Perceptron with Binary Synapses
2009 Baldassi, Carlo
Efficient supervised learning in networks with binary synapses
2007 Baldassi, Carlo; Braunstein, Alfredo; Brunei, N; Zecchina, Riccardo
Citazione | Data di pubblicazione | Autori | File |
---|---|---|---|
Learning through atypical phase transitions in overparameterized neural networks / Baldassi, C.; Lauditi, C.; Malatesta, E. M.; Pacelli, R.; Perugini, G.; Zecchina, R.. - In: PHYSICAL REVIEW. E. - ISSN 2470-0053. - 106:1(2022), p. 014116. [10.1103/PhysRevE.106.014116] | 1-gen-2022 | Baldassi C.Lauditi C.Pacelli R.Perugini G.Zecchina R. + | 2110.00683.pdf |
Wide flat minima and optimal generalization in classifying high-dimensional Gaussian mixtures / Baldassi, Carlo; Malatesta, Enrico M; Negri, Matteo; Zecchina, Riccardo. - In: JOURNAL OF STATISTICAL MECHANICS: THEORY AND EXPERIMENT. - ISSN 1742-5468. - ELETTRONICO. - 2020:12(2020). [10.1088/1742-5468/abcd31] | 1-gen-2020 | Baldassi, CarloNegri, MatteoZecchina, Riccardo + | Baldassi_2020_J._Stat._Mech._2020_124012.pdf; 2010.14761.pdf |
From inverse problems to learning: A Statistical Mechanics approach / Baldassi, Carlo; Gerace, Federica; Saglietti, Luca; Zecchina, Riccardo. - In: JOURNAL OF PHYSICS. CONFERENCE SERIES. - ISSN 1742-6588. - 955:1(2018), p. 012001. [10.1088/1742-6596/955/1/012001] | 1-gen-2018 | Baldassi, CarloGerace, FedericaSaglietti, LucaZecchina, Riccardo | - |
Role of Synaptic Stochasticity in Training Low-Precision Neural Networks / Baldassi, Carlo; Federica, Gerace; Kappen, Hilbert J.; Lucibello, Carlo; Luca, Saglietti; Tartaglione, Enzo; Zecchina, Riccardo. - In: PHYSICAL REVIEW LETTERS. - ISSN 1092-0145. - 120:(2018). [10.1103/PhysRevLett.120.268103] | 1-gen-2018 | Carlo BaldassiLUCIBELLO, CARLOEnzo TartaglioneRiccardo Zecchina + | - |
A method to reduce the rejection rate in Monte Carlo Markov chains / Baldassi, Carlo. - In: JOURNAL OF STATISTICAL MECHANICS: THEORY AND EXPERIMENT. - ISSN 1742-5468. - ELETTRONICO. - 2017:3(2017), p. 033301. [10.1088/1742-5468/aa5335] | 1-gen-2017 | BALDASSI, CARLO | rrrmc.pdf |
RNAs competing for microRNAs mutually influence their fluctuations in a highly non-linear microRNA-dependent manner in single cells / Bosia, Carla; Sgrò, Francesco; Conti, Laura; Baldassi, Carlo; Cavallo, Federica; Di Cunto, Ferdinando; Turco, Emilia; Pagnani, Andrea; Zecchina, Riccardo. - In: GENOME BIOLOGY. - ISSN 1474-760X. - ELETTRONICO. - 18:(2017), pp. 17-30. [10.1186/s13059-017-1162-x] | 1-gen-2017 | BOSIA, CARLABALDASSI, CARLOPAGNANI, ANDREA + | s13059-017-1162-x.pdf |
Learning may need only a few bits of synaptic precision / Baldassi, Carlo; Gerace, Federica; Lucibello, Carlo; Saglietti, Luca; Zecchina, Riccardo. - In: PHYSICAL REVIEW. E. - ISSN 2470-0045. - ELETTRONICO. - 93:5(2016), p. 052313. [10.1103/PhysRevE.93.052313] | 1-gen-2016 | BALDASSI, CARLOGERACE, FEDERICALUCIBELLO, CARLOSAGLIETTI, LUCAZECCHINA, RICCARDO | fewbits.pdf |
Local entropy as a measure for sampling solutions in constraint satisfaction problems / Baldassi, Carlo; Ingrosso, Alessandro; Lucibello, Carlo; Saglietti, Luca; Zecchina, Riccardo. - In: JOURNAL OF STATISTICAL MECHANICS: THEORY AND EXPERIMENT. - ISSN 1742-5468. - ELETTRONICO. - 2016:2(2016), p. 023301. [10.1088/1742-5468/2016/02/023301] | 1-gen-2016 | BALDASSI, CARLOINGROSSO, ALESSANDROLUCIBELLO, CARLOSAGLIETTI, LUCAZECCHINA, RICCARDO | - |
Simultaneous identification of specifically interacting paralogs and interprotein contacts by direct coupling analysis / Gueudre, Thomas; Baldassi, Carlo; Zamparo, Marco; Weigt, Martin; Pagnani, Andrea. - In: PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA. - ISSN 0027-8424. - STAMPA. - 113:43(2016), pp. 12186-12191. [10.1073/pnas.1607570113] | 1-gen-2016 | GUEUDRE, THOMASBALDASSI, CARLOZAMPARO, MARCOPAGNANI, ANDREA + | PNAS-2016-Gueudré-12186-91.pdf |
Unreasonable effectiveness of learning neural networks: From accessible states and robust ensembles to basic algorithmic schemes / Baldassi, Carlo; Borgs, Christian; Chayes, Jennifer T; Ingrosso, Alessandro; Lucibello, Carlo; Saglietti, Luca; Zecchina, Riccardo. - In: PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA. - ISSN 0027-8424. - STAMPA. - 113:48(2016), pp. E7655-E7662. [10.1073/pnas.1608103113] | 1-gen-2016 | BALDASSI, CARLOINGROSSO, ALESSANDROLUCIBELLO, CARLOSAGLIETTI, LUCAZECCHINA, RICCARDO + | accessible-arxiv.pdf |
A Max-Sum algorithm for training discrete neural networks / Baldassi, Carlo; Braunstein, Alfredo. - In: JOURNAL OF STATISTICAL MECHANICS: THEORY AND EXPERIMENT. - ISSN 1742-5468. - ELETTRONICO. - 2015:8(2015), p. P08008. [10.1088/1742-5468/2015/08/P08008] | 1-gen-2015 | BALDASSI, CARLOBRAUNSTEIN, ALFREDO | - |
A Three-Threshold Learning Rule Approaches the Maximal Capacity of Recurrent Neural Networks / Alemi, Alireza; Baldassi, Carlo; Brunel, Nicolas; Zecchina, Riccardo. - In: PLOS COMPUTATIONAL BIOLOGY. - ISSN 1553-734X. - ELETTRONICO. - 11:8(2015), p. e1004439. [10.1371/journal.pcbi.1004439] | 1-gen-2015 | BALDASSI, CARLOBRUNEL, NICOLASZECCHINA, RICCARDO + | A Three-Threshold Learning Rule Approaches the Maximal Capacity of Recurrent Neural Networks.pdf |
Subdominant Dense Clusters Allow for Simple Learning and High Computational Performance in Neural Networks with Discrete Synapses / Baldassi, Carlo; Ingrosso, Alessandro; Lucibello, Carlo; Saglietti, Luca; Zecchina, Riccardo. - In: PHYSICAL REVIEW LETTERS. - ISSN 0031-9007. - ELETTRONICO. - 115:12(2015), p. 128101. [10.1103/PhysRevLett.115.128101] | 1-gen-2015 | BALDASSI, CARLOINGROSSO, ALESSANDROLUCIBELLO, CARLOSAGLIETTI, LUCAZECCHINA, RICCARDO | 1509.05753v1.pdf |
Fast and Accurate Multivariate Gaussian Modeling of Protein Families: Predicting Residue Contacts and Protein-Interaction Partners / Baldassi, Carlo; Zamparo, Marco; Feinauer, Christoph; Procaccini, A.; Zecchina, Riccardo; Weigt, R.; Pagnani, Andrea. - In: PLOS ONE. - ISSN 1932-6203. - ELETTRONICO. - 9:(2014), p. e92721. [10.1371/journal.pone.0092721] | 1-gen-2014 | BALDASSI, CARLOZAMPARO, MARCOFEINAUER, CHRISTOPHZECCHINA, RICCARDOPAGNANI, ANDREA + | journal.pone.0092721.pdf; GaussDCA-matlab.tgz; GaussDCA-julia.tgz |
Shape similarity, better than semantic membership, accounts for the structure of visual object representations in a population of monkey inferotemporal neurons / Baldassi, Carlo; Alemi Neissi, A.; Pagan, M.; Dicarlo, J.; Zecchina, Riccardo; Zoccolan, D.. - In: PLOS COMPUTATIONAL BIOLOGY. - ISSN 1553-7358. - ELETTRONICO. - 9:(2013), p. e1003167. [10.1371/journal.pcbi.1003167] | 1-gen-2013 | BALDASSI, CARLOZECCHINA, RICCARDO + | journal.pcbi.1003167.pdf |
Theory and learning protocols for the material tempotron model / Baldassi, Carlo; Braunstein, Alfredo; Zecchina, Riccardo. - In: JOURNAL OF STATISTICAL MECHANICS: THEORY AND EXPERIMENT. - ISSN 1742-5468. - ELETTRONICO. - 2013:(2013), p. P12013. [10.1088/1742-5468/2013/12/P12013] | 1-gen-2013 | BALDASSI, CARLOBRAUNSTEIN, ALFREDOZECCHINA, RICCARDO | 1309.0393.pdf |
Generalization Learning in a Perceptron with Binary Synapses / Baldassi, Carlo. - In: JOURNAL OF STATISTICAL PHYSICS. - ISSN 0022-4715. - ELETTRONICO. - 136:(2009), pp. 902-916. [10.1007/s10955-009-9822-1] | 1-gen-2009 | BALDASSI, CARLO | - |
Efficient supervised learning in networks with binary synapses / Baldassi, Carlo; Braunstein, Alfredo; Brunei, N; Zecchina, Riccardo. - In: PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA. - ISSN 0027-8424. - 104:(2007), pp. 11079-11084. [10.1073/pnas.0700324104] | 1-gen-2007 | BALDASSI, CARLOBRAUNSTEIN, ALFREDOZECCHINA, RICCARDO + | - |