Carlo Baldassi

39 papers A* 2Misc 1Journal 33Unranked 1

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	BEP: A Binary Error Propagation Algorithm for Binary Neural Networks Training. CoRR Luca Colombo, Fabrizio Pittorino, Daniele Zambon, Carlo Baldassi, Manuel Roveri, Cesare Alippi
2025	J	`jnl`	Dynamical Learning in Deep Asymmetric Recurrent Neural Networks. CoRR Davide Badalotti, Carlo Baldassi, Marc Mézard, Mattia Scardecchia, Riccardo Zecchina
2025	J	`jnl`	Sampling through Algorithmic Diffusion in non-convex Perceptron problems. CoRR Elizaveta Demyanenko, Davide Straziota, Carlo Baldassi, Carlo Lucibello
2023	J	`jnl`	Typical and atypical solutions in non-convex neural networks with discrete and continuous weights. CoRR Carlo Baldassi, Enrico M. Malatesta, Gabriele Perugini, Riccardo Zecchina
2022	A*	`conf`	Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry. ICML Fabrizio Pittorino, Antonio Ferraro, Gabriele Perugini, Christoph Feinauer, Carlo Baldassi, Riccardo Zecchina
2022	J	`jnl`	Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry. CoRR Fabrizio Pittorino, Antonio Ferraro, Gabriele Perugini, Christoph Feinauer, Carlo Baldassi, Riccardo Zecchina
2022	J	`jnl`	Recombinator-k-Means: An Evolutionary Algorithm That Exploits k-Means++ for Recombination. IEEE Trans. Evol. Comput. Carlo Baldassi
2022	J	`jnl`	Systematically and efficiently improving Trans. Mach. Learn. Res. Carlo Baldassi
2022	J	`jnl`	Systematically improving existing k-means initialization algorithms at nearly no cost, by pairwise-nearest-neighbor smoothing. CoRR Carlo Baldassi
2021	A*	`conf`	Entropic gradient descent algorithms and wide flat minima. ICLR Fabrizio Pittorino, Carlo Lucibello, Christoph Feinauer, Gabriele Perugini, Carlo Baldassi, Elizaveta Demyanenko, Riccardo Zecchina
2021	J	`jnl`	Learning through atypical "phase transitions" in overparameterized neural networks. CoRR Carlo Baldassi, Clarissa Lauditi, Enrico M. Malatesta, Rosalba Pacelli, Gabriele Perugini, Riccardo Zecchina
2021	J	`jnl`	Quantum Approximate Optimization Algorithm applied to the binary perceptron. CoRR Pietro Torta, Glen B. Mbeng, Carlo Baldassi, Riccardo Zecchina, Giuseppe E. Santoro
2021	J	`jnl`	Unveiling the structure of wide flat minima in neural networks. CoRR Carlo Baldassi, Clarissa Lauditi, Enrico M. Malatesta, Gabriele Perugini, Riccardo Zecchina
2020	J	`jnl`	A Behavioral Characterization of the Drift Diffusion Model and Its Multialternative Extension for Choice Under Time Pressure. Manag. Sci. Carlo Baldassi, Simone Cerreia-Vioglio, Fabio Maccheroni, Massimo Marinacci, Marco Pirazzini
2020	J	`jnl`	Entropic gradient descent algorithms and wide flat minima. CoRR Fabrizio Pittorino, Carlo Lucibello, Christoph Feinauer, Enrico M. Malatesta, Gabriele Perugini, Carlo Baldassi, Matteo Negri, Elizaveta Demyanenko, Riccardo Zecchina
2020	J	`jnl`	Ergodic Annealing. CoRR Carlo Baldassi, Fabio Maccheroni, Massimo Marinacci, Marco Pirazzini
2020	J	`jnl`	Multialternative Neural Decision Process. CoRR Carlo Baldassi, Simone Cerreia-Vioglio, Fabio Maccheroni, Massimo Marinacci, Marco Pirazzini
2020	—	`ch.`	Predicting Interacting Protein Pairs by Coevolutionary Paralog Matching. Protein-Protein Interaction Networks Thomas Gueudré, Carlo Baldassi, Andrea Pagnani, Martin Weigt
2020	J	`jnl`	Shaping the learning landscape in neural networks around wide flat minima. Proc. Natl. Acad. Sci. USA Carlo Baldassi, Fabrizio Pittorino, Riccardo Zecchina
2020	J	`jnl`	Wide flat minima and optimal generalization in classifying high-dimensional Gaussian mixtures. CoRR Carlo Baldassi, Enrico M. Malatesta, Matteo Negri, Riccardo Zecchina
2019	J	`jnl`	Natural representation of composite data with replicated autoencoders. CoRR Matteo Negri, Davide Bergamini, Carlo Baldassi, Riccardo Zecchina, Christoph Feinauer
2019	J	`jnl`	On the geometry of solutions and on the capacity of multi-layer neural networks with ReLU activations. CoRR Carlo Baldassi, Enrico M. Malatesta, Riccardo Zecchina
2019	J	`jnl`	Recombinator-k-means: Enhancing k-means++ by seeding from pools of previous runs. CoRR Carlo Baldassi
2019	J	`jnl`	Shaping the learning landscape in neural networks around wide flat minima. CoRR Carlo Baldassi, Fabrizio Pittorino, Riccardo Zecchina
2018	J	`jnl`	Efficiency of quantum vs. classical annealing in nonconvex learning problems. Proc. Natl. Acad. Sci. USA Carlo Baldassi, Riccardo Zecchina
2017	J	`jnl`	Efficiency of quantum versus classical annealing in non-convex learning problems. CoRR Carlo Baldassi, Riccardo Zecchina
2017	—	`conf`	Entropy-SGD: Biasing Gradient Descent Into Wide Valleys. ICLR (Poster) Pratik Chaudhari, Anna Choromanska, Stefano Soatto, Yann LeCun, Carlo Baldassi, Christian Borgs, Jennifer T. Chayes, Levent Sagun, Riccardo Zecchina
2017	J	`jnl`	On the role of synaptic stochasticity in training low-precision neural networks. CoRR Carlo Baldassi, Federica Gerace, Hilbert J. Kappen, Carlo Lucibello, Luca Saglietti, Enzo Tartaglione, Riccardo Zecchina
2017	J	`jnl`	Parle: parallelizing stochastic gradient descent. CoRR Pratik Chaudhari, Carlo Baldassi, Riccardo Zecchina, Stefano Soatto, Ameet Talwalkar
2016	J	`jnl`	Entropy-SGD: Biasing Gradient Descent Into Wide Valleys. CoRR Pratik Chaudhari, Anna Choromanska, Stefano Soatto, Yann LeCun, Carlo Baldassi, Christian Borgs, Jennifer T. Chayes, Levent Sagun, Riccardo Zecchina
2016	J	`jnl`	Unreasonable Effectiveness of Learning Neural Nets: Accessible States and Robust Ensembles. CoRR Carlo Baldassi, Christian Borgs, Jennifer T. Chayes, Alessandro Ingrosso, Carlo Lucibello, Luca Saglietti, Riccardo Zecchina
2016	J	`jnl`	Unreasonable effectiveness of learning neural networks: From accessible states and robust ensembles to basic algorithmic schemes. Proc. Natl. Acad. Sci. USA Carlo Baldassi, Christian Borgs, Jennifer T. Chayes, Alessandro Ingrosso, Carlo Lucibello, Luca Saglietti, Riccardo Zecchina
2015	J	`jnl`	A Max-Sum algorithm for training discrete neural networks. CoRR Carlo Baldassi, Alfredo Braunstein
2015	J	`jnl`	A Three-Threshold Learning Rule Approaches the Maximal Capacity of Recurrent Neural Networks. PLoS Comput. Biol. Alireza Alemi, Carlo Baldassi, Nicolas Brunel, Riccardo Zecchina
2015	—	`ch.`	Binary Synapse Circuitry for High Efficiency Learning Algorithm Using Generalized Boundary Condition Memristor Models. Advances in Neural Networks Jacopo Secco, Alessandro Vinassa, Valentina Pontrandolfo, Carlo Baldassi, Fernando Corinto
2014	Misc	`conf`	Sharing Information to Reconstruct Patient-Specific Pathways in Heterogeneous Diseases. Pacific Symposium on Biocomputing Anthony Gitter, Alfredo Braunstein, Andrea Pagnani, Carlo Baldassi, Christian Borgs, Jennifer T. Chayes, Riccardo Zecchina, Ernest Fraenkel
2013	J	`jnl`	Shape Similarity, Better than Semantic Membership, Accounts for the Structure of Visual Object Representations in a Population of Monkey Inferotemporal Neurons. PLoS Comput. Biol. Carlo Baldassi, Alireza Alemi-Neissi, Marino Pagan, James J. DiCarlo, Riccardo Zecchina, Davide Zoccolan
2007	J	`jnl`	Efficient supervised learning in networks with binary synapses CoRR Carlo Baldassi, Alfredo Braunstein, Nicolas Brunel, Riccardo Zecchina
2007	J	`jnl`	Efficient supervised learning in networks with binary synapses. Proc. Natl. Acad. Sci. USA Carlo Baldassi, Alfredo Braunstein, Nicolas Brunel, Riccardo Zecchina