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
Align, then memorise: the dynamics of learning with feedback alignment
Refinetti, Maria, d’Ascoli, Stéphane, Ohana, Ruben, Goldt, Sebastian
Published in Journal of physics. A, Mathematical and theoretical (28.01.2022)
Published in Journal of physics. A, Mathematical and theoretical (28.01.2022)
Get full text
Journal Article
Align, then memorise: the dynamics of learning with feedback alignment
Refinetti, Maria, d’Ascoli, Stéphane, Ohana, Ruben, Goldt, Sebastian
Published in Journal of statistical mechanics (01.11.2022)
Published in Journal of statistical mechanics (01.11.2022)
Get full text
Journal Article
Triple descent and the two kinds of overfitting: where and why do they appear?
d’Ascoli, Stéphane, Sagun, Levent, Biroli, Giulio
Published in Journal of statistical mechanics (01.12.2021)
Published in Journal of statistical mechanics (01.12.2021)
Get full text
Journal Article
ConViT: improving vision transformers with soft convolutional inductive biases
d’Ascoli, Stéphane, Touvron, Hugo, Leavitt, Matthew L, Morcos, Ari S, Biroli, Giulio, Sagun, Levent
Published in Journal of statistical mechanics (01.11.2022)
Published in Journal of statistical mechanics (01.11.2022)
Get full text
Journal Article
A jamming transition from under- to over-parametrization affects generalization in deep learning
Spigler, S, Geiger, M, d'Ascoli, S, Sagun, L, Biroli, G, Wyart, M
Published in Journal of physics. A, Mathematical and theoretical (22.11.2019)
Published in Journal of physics. A, Mathematical and theoretical (22.11.2019)
Get full text
Journal Article
Align, then memorise: the dynamics of learning with feedback alignment This is a lightly edited version of an article that appeared previously in the proceedings of the 38th International Conference on Machine Learning (ICML) in 2021 [1]
Refinetti, Maria, d’Ascoli, Stéphane, Ohana, Ruben, Goldt, Sebastian
Published in Journal of physics. A, Mathematical and theoretical (28.01.2022)
Published in Journal of physics. A, Mathematical and theoretical (28.01.2022)
Get full text
Journal Article
ODEFormer: Symbolic Regression of Dynamical Systems with Transformers
d'Ascoli, Stéphane, Becker, Sören, Mathis, Alexander, Schwaller, Philippe, Kilbertus, Niki
Year of Publication 09.10.2023
Year of Publication 09.10.2023
Get full text
Journal Article
Boolformer: Symbolic Regression of Logic Functions with Transformers
d'Ascoli, Stéphane, Bengio, Samy, Susskind, Josh, Abbé, Emmanuel
Published in arXiv.org (21.09.2023)
Published in arXiv.org (21.09.2023)
Get full text
Paper
Journal Article
Triple descent and the two kinds of overfitting: where and why do they appear? This article is an updated version of: Ascoli S, Sagun L and Biroli G 2020 Triple descent and the two kinds of overfitting: where and why do they appear? Advances in Neural Information Processing Systems vol 33 ed H Larochelle, M Ranzato, R Hadsell, M F Balcan and H Lin (New York: Curran Associates)
d’Ascoli, Stéphane, Sagun, Levent, Biroli, Giulio
Published in Journal of statistical mechanics (29.12.2021)
Published in Journal of statistical mechanics (29.12.2021)
Get full text
Journal Article
Triple descent and the two kinds of overfitting: Where & why do they appear?
Get full text
Paper
Journal Article
On the interplay between data structure and loss function in classification problems
d'Ascoli, Stéphane, Gabrié, Marylou, Sagun, Levent, Biroli, Giulio
Published in arXiv.org (12.10.2021)
Published in arXiv.org (12.10.2021)
Get full text
Paper
Journal Article
Length Generalization in Arithmetic Transformers
Jelassi, Samy, d'Ascoli, Stéphane, Domingo-Enrich, Carles, Wu, Yuhuai, Li, Yuanzhi, Charton, François
Published in arXiv.org (27.06.2023)
Published in arXiv.org (27.06.2023)
Get full text
Paper
Journal Article
Align, then memorise: the dynamics of learning with feedback alignment
Refinetti, Maria, d'Ascoli, Stéphane, Ohana, Ruben, Goldt, Sebastian
Published in arXiv.org (10.06.2021)
Published in arXiv.org (10.06.2021)
Get full text
Paper
Journal Article
Align, then memorise: the dynamics of learning with feedback alignment This article is an updated version of: Refinetti M, D’Ascoli S, Ohana R and Goldt S 2021 Align, then memorise: the dynamics of learning with feedback alignment Proc. 38th Int. Conf. Machine Learning vol 139 ed M Meila and T Zhang pp 8925–35
Refinetti, Maria, d’Ascoli, Stéphane, Ohana, Ruben, Goldt, Sebastian
Published in Journal of statistical mechanics (01.11.2022)
Published in Journal of statistical mechanics (01.11.2022)
Get full text
Journal Article