Fetching the paper…
Reading the bibliography…
Learning in Deep Neural Networks (DNN) takes place by minimizing a non-convex high-dimensional loss function, typically by a stochastic gradient descent (SGD) strategy.
Spin glass theory and beyond: An Introduction to the Replica Method and Its Applications , volume 9
Marc Mézard, Giorgio Parisi, and Miguel Virasoro · 1987
Earlier work this paper cites.
Storage capacity of memory networks with binary couplings
Werner Krauth and Marc Mézard · 1989
Earlier work this paper cites.
Bounds on the learning capacity of some multi-layer networks
Graeme Mitchison and Richard Durbin · 1989
Earlier work this paper cites.
Statistical mechanics of a multilayered neural network
Eli Barkai, David Hansel, and Ido Kanter · 1990
Earlier work this paper cites.
Broken symmetries in multilayered perceptrons
Eli Barkai, David Hansel, and Haim Sompolinsky · 1992
Earlier work this paper cites.
Storage capacity and learning algorithms for two-layer neural networks
A. Engel, H. M. Köhler, F. Tschepke, H. Vollmayr, and A. Zippelius · 1992
Earlier work this paper cites.
Dynamics of learning for the binary perceptron problem
Heinz Horner · 1992
Earlier work this paper cites.
Generalization in a large committee machine
Holm Schwarze and John Hertz · 1992
Earlier work this paper cites.
Recipes for metastable states in spin glasses
Silvio Franz and Giorgio Parisi · 1995
Earlier work this paper cites.
Structural glass transition and the entropy of the metastable states
Rémi Monasson · 1995
Cited alongside, same era.
Weight space structure and internal representations: a direct approach to learning and generalization in multilayer neural networks
Rémi Monasson and Riccardo Zecchina · 1995
Cited alongside, same era.
Statistical mechanics of learning
Andreas Engel and Christian Van den Broeck · 2001
Cited alongside, same era.
Information theory, inference and learning algorithms
David JC MacKay · 2003
Cited alongside, same era.
Learning by message passing in networks of discrete synapses
Alfredo Braunstein and Riccardo Zecchina · 2006
Cited alongside, same era.
Weight distribution of low-density parity-check codes
Changyan Di, Thomas J Richardson, and Ruediger L Urbanke · 2006
Cited alongside, same era.
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, and Riccardo Zecchina · 2015
Later among the works it cites.
Deep learning
Yann LeCun, Yoshua Bengio, and Geoffrey Hinton · 2015
Later among the works it cites.
Local entropy as a measure for sampling solutions in constraint satisfaction problems
Carlo Baldassi, Alessandro Ingrosso, Carlo Lucibello, Luca Saglietti, and Riccardo Zecchina · 2016
Later among the works it cites.
On large-batch training for deep learning: Generalization gap and sharp minima
Nitish Shirish Keskar, Dheevatsa Mudigere, Jorge Nocedal, Mikhail Smelyanskiy, and Ping Tak Peter Tang · 2016
Later among the works it cites.
Statistical Physics, Optimization, Inference, and Message-Passing Algorithms: Lecture Notes of the Les Houches School of Physics-Special Issue, October 2013
Florent Krzakala, Federico Ricci-Tersenghi, Lenka Zdeborova, Riccardo Zecchina, Eric W Tramel, and Leticia F Cugliandolo · 2016
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Efficient supervised learning in networks with binary synapses
Carlo Baldassi, Alfredo Braunstein, Nicolas Brunel, and Riccardo Zecchina · 2007
Cited alongside, same era.
Generalization learning in a perceptron with binary synapses
Carlo Baldassi · 2009
Cited alongside, same era.
Origin of the computational hardness for learning with binary synapses
Haiping Huang and Yoshiyuki Kabashima · 2014
Cited alongside, same era.
Unreasonable effectiveness of learning neural networks: From accessible states and robust ensembles to basic algorithmic schemes
Carlo Baldassi, Christian Borgs, Jennifer T. Chayes, Alessandro Ingrosso, Carlo Lucibello, Luca Saglietti, and Riccardo Zecchina
Cited in the paper.
Learning may need only a few bits of synaptic precision
Carlo Baldassi, Federica Gerace, Carlo Lucibello, Luca Saglietti, and Riccardo Zecchina
Cited in the paper.
Later among the works it cites.
Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms, 2017
Han Xiao, Kashif Rasul, and Roland Vollgraf · 2017
Later among the works it cites.
Role of synaptic stochasticity in training low-precision neural networks
Carlo Baldassi, Federica Gerace, Hilbert J Kappen, Carlo Lucibello, Luca Saglietti, Enzo Tartaglione, and Riccardo Zecchina · 2018
Later among the works it cites.
Properties of the geometry of solutions and capacity of multilayer neural networks with rectified linear unit activations
Carlo Baldassi, Enrico M Malatesta, and Riccardo Zecchina · 2019
Closest in time.
Capacity lower bound for the ising perceptron
Jian Ding and Nike Sun · 2019
Closest in time.