C
Carlo Baldassi
Researcher at Bocconi University
Publications - 65
Citations - 2313
Carlo Baldassi is an academic researcher from Bocconi University. The author has contributed to research in topics: Artificial neural network & Perceptron. The author has an hindex of 21, co-authored 60 publications receiving 1880 citations. Previous affiliations of Carlo Baldassi include Polytechnic University of Turin & Institute for Scientific Interchange.
Papers
More filters
Posted Content
Entropy-SGD: Biasing Gradient Descent Into Wide Valleys
Pratik Chaudhari,Pratik Chaudhari,Anna Choromanska,Stefano Soatto,Yann LeCun,Yann LeCun,Carlo Baldassi,Carlo Baldassi,Christian Borgs,Jennifer Chayes,Levent Sagun,Riccardo Zecchina,Riccardo Zecchina +12 more
TL;DR: This paper proposes a new optimization algorithm called Entropy-SGD for training deep neural networks that is motivated by the local geometry of the energy landscape and compares favorably to state-of-the-art techniques in terms of generalization error and training time.
Proceedings Article
Entropy-SGD: Biasing Gradient Descent Into Wide Valleys.
Pratik Chaudhari,Anna Choromanska,Stefano Soatto,Yann LeCun,Carlo Baldassi,Christian Borgs,Jennifer Chayes,Levent Sagun,Riccardo Zecchina +8 more
TL;DR: In this article, a local-entropy-based objective function is proposed for training deep neural networks that is motivated by the local geometry of the energy landscape, where the gradient of the local entropy is computed before each update of the weights.
Journal ArticleDOI
Fast and Accurate Multivariate Gaussian Modeling of Protein Families: Predicting Residue Contacts and Protein-Interaction Partners
Carlo Baldassi,Marco Zamparo,Christoph Feinauer,Andrea Procaccini,Riccardo Zecchina,Martin Weigt,Andrea Pagnani +6 more
TL;DR: The quality of inference is comparable or superior to the one achieved by mean-field approximations to inference with discrete variables, as done by direct-coupling analysis for the prediction of residue-residue contacts in proteins and the identification of protein-protein interaction partner in bacterial signal transduction.
Journal ArticleDOI
Unreasonable Effectiveness of Learning Neural Networks: From Accessible States and Robust Ensembles to Basic Algorithmic Schemes
Carlo Baldassi,Christian Borgs,Jennifer Chayes,Alessandro Ingrosso,Carlo Lucibello,Luca Saglietti,Riccardo Zecchina +6 more
TL;DR: It is shown that there are regions of the optimization landscape that are both robust and accessible and that their existence is crucial to achieve good performance on a class of particularly difficult learning problems, and an explanation of this good performance is proposed in terms of a nonequilibrium statistical physics framework.
Journal ArticleDOI
Subdominant Dense Clusters Allow for Simple Learning and High Computational Performance in Neural Networks with Discrete Synapses
Carlo Baldassi,Alessandro Ingrosso,Carlo Lucibello,Luca Saglietti,Riccardo Zecchina,Riccardo Zecchina +5 more
TL;DR: It is shown that discrete synaptic weights can be efficiently used for learning in large scale neural systems, and lead to unanticipated computational performance, and that these synaptic configurations are robust to perturbations and generalize better than typical solutions.