Asymptotic learning curves of kernel methods: empirical data versus teacher-student paradigm
Spigler, Stefano, Geiger, Mario, Wyart, Matthieu
Published in Journal of statistical mechanics (21.12.2020)
Published in Journal of statistical mechanics (21.12.2020)
Get full text
Journal Article
Disentangling feature and lazy training in deep neural networks
Geiger, Mario, Spigler, Stefano, Jacot, Arthur, Wyart, Matthieu
Published in Journal of statistical mechanics (01.11.2020)
Published in Journal of statistical mechanics (01.11.2020)
Get full text
Journal Article
Scaling description of generalization with number of parameters in deep learning
Geiger, Mario, Jacot, Arthur, Spigler, Stefano, Gabriel, Franck, Sagun, Levent, d'Ascoli, Stéphane, Biroli, Giulio, Hongler, Clément, Wyart, Matthieu
Published in Journal of statistical mechanics (01.02.2020)
Published in Journal of statistical mechanics (01.02.2020)
Get full text
Journal Article
How isotropic kernels perform on simple invariants
Paccolat, Jonas, Spigler, Stefano, Wyart, Matthieu
Published in Machine learning: science and technology (01.06.2021)
Published in Machine learning: science and technology (01.06.2021)
Get full text
Journal Article
Comparing dynamics: deep neural networks versus glassy systems
Baity-Jesi, Marco, Sagun, Levent, Geiger, Mario, Spigler, Stefano, Ben Arous, Gérard, Cammarota, Chiara, LeCun, Yann, Wyart, Matthieu, Biroli, Giulio
Published in Journal of statistical mechanics (20.12.2019)
Published in Journal of statistical mechanics (20.12.2019)
Get full text
Journal Article
Comparing dynamics: deep neural networks versus glassy systemsThis article is an updated version of a paper presented at ICML 2018, and is present in the following informal collection of proceedings: 2018 Proceedings Of Machine Learning Research 80 324-333
Baity-Jesi, Marco, Sagun, Levent, Geiger, Mario, Spigler, Stefano, Ben Arous, Gérard, Cammarota, Chiara, LeCun, Yann, Wyart, Matthieu, Biroli, Giulio
Published in Journal of statistical mechanics (20.12.2019)
Published in Journal of statistical mechanics (20.12.2019)
Get full text
Journal Article
A jamming transition from under- to over-parametrization affects loss landscape and generalization
Spigler, Stefano, Geiger, Mario, d'Ascoli, Stéphane, Sagun, Levent, Biroli, Giulio, Wyart, Matthieu
Published in arXiv.org (18.06.2019)
Published in arXiv.org (18.06.2019)
Get full text
Paper
Journal Article
The jamming transition as a paradigm to understand the loss landscape of deep neural networks
Geiger, Mario, Spigler, Stefano, d'Ascoli, Stéphane, Sagun, Levent, Baity-Jesi, Marco, Biroli, Giulio, Wyart, Matthieu
Published in arXiv.org (17.06.2019)
Published in arXiv.org (17.06.2019)
Get full text
Paper
Journal Article
Scaling description of generalization with number of parameters in deep learning
Geiger, Mario, Jacot, Arthur, Spigler, Stefano, Franck, Gabriel, Sagun, Levent, d'Ascoli, Stéphane, Biroli, Giulio, Hongler, Clément, Wyart, Matthieu
Published in arXiv.org (08.10.2019)
Published in arXiv.org (08.10.2019)
Get full text
Paper
Journal Article