Neural tangent kernel: Convergence and generalization in neural networks A Jacot, F Gabriel, C Hongler
Advances in neural information processing systems 31, 2018
3036 2018 Scaling description of generalization with number of parameters in deep learning M Geiger, A Jacot, S Spigler, F Gabriel, L Sagun, S d’Ascoli, G Biroli, ...
Journal of Statistical Mechanics: Theory and Experiment 2020 (2), 023401, 2020
208 2020 Implicit regularization of random feature models A Jacot, B Simsek, F Spadaro, C Hongler, F Gabriel
International Conference on Machine Learning, 4631-4640, 2020
89 2020 Geometric stochastic heat equations Y Bruned, F Gabriel, M Hairer, L Zambotti
Journal of the American Mathematical Society 35 (1), 1-80, 2022
54 2022 Kernel alignment risk estimator: Risk prediction from training data A Jacot, B Simsek, F Spadaro, C Hongler, F Gabriel
Advances in neural information processing systems 33, 15568-15578, 2020
54 2020 Saddle-to-saddle dynamics in deep linear networks: Small initialization training, symmetry, and sparsity A Jacot, F Ged, B Şimşek, C Hongler, F Gabriel
arXiv preprint arXiv:2106.15933, 2021
32 2021 The asymptotic spectrum of the hessian of dnn throughout training A Jacot, F Gabriel, C Hongler
arXiv preprint arXiv:1910.02875, 2019
29 2019 The Makeenko–Migdal equation for Yang–Mills theory on compact surfaces BK Driver, F Gabriel, BC Hall, T Kemp
Communications in Mathematical Physics 352 (3), 967-978, 2017
29 2017 Combinatorial theory of permutation-invariant random matrices I: Partitions, geometry and renormalization F Gabriel
arXiv preprint arXiv:1503.02792, 2015
22 2015 Freeness over the diagonal for large random matrices B Au, G Cébron, A Dahlqvist, F Gabriel, C Male
21 * 2021 Combinatorial theory of permutation-invariant random matrices II: cumulants, freeness and Levy processes F Gabriel
arXiv preprint arXiv:1507.02465, 2015
19 2015 Freeze and chaos for dnns: an ntk view of batch normalization, checkerboard and boundary effects A Jacot, F Gabriel, C Hongler
arXiv preprint arXiv:1907.05715 6, 2019
18 2019 The generalized master fields G Cébron, A Dahlqvist, F Gabriel
Journal of Geometry and Physics 119, 34-53, 2017
18 * 2017 Deep linear networks dynamics: Low-rank biases induced by initialization scale and l2 regularization A Jacot, F Ged, F Gabriel, B Simsek, C Hongler
arXiv preprint arXiv:2106.15933 3, 2021
15 2021 Insider trading with penalties S Carré, P Collin-Dufresne, F Gabriel
Journal of Economic Theory 203, 105461, 2022
10 2022 Freeness of type and conditional freeness for random matrices G Cébron, A Dahlqvist, F Gabriel
arXiv preprint arXiv:2205.01926, 2022
10 2022 A combinatorial theory of random matrices III: random walks on S (N), ramified coverings and the S (∞) Yang-Mills measure F Gabriel
arXiv preprint arXiv:1510.01046, 2015
10 2015 Feature Learning in -regularized DNNs: Attraction/Repulsion and Sparsity A Jacot, E Golikov, C Hongler, F Gabriel
Advances in Neural Information Processing Systems 35, 6763-6774, 2022
9 2022 Planar Markovian holonomy fields F Gabriel
arXiv preprint arXiv:1501.05077, 2015
7 * 2015 Traffic-partition correspondence G Cébron, A Dahlqvist, F Gabriel, C Male
Work in progress, 0
7