Neural tangent kernel: Convergence and generalization in neural networks A Jacot, F Gabriel, C Hongler
Advances in neural information processing systems 31, 2018
3821 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
237 2020 Disentangling feature and lazy training in deep neural networks M Geiger, S Spigler, A Jacot, M Wyart
Journal of Statistical Mechanics: Theory and Experiment 2020 (11), 113301, 2020
169 * 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
106 2020 Geometry of the loss landscape in overparameterized neural networks: Symmetries and invariances B Simsek, F Ged, A Jacot, F Spadaro, C Hongler, W Gerstner, J Brea
International Conference on Machine Learning, 9722-9732, 2021
97 2021 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
68 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
67 * 2021 Implicit bias of large depth networks: a notion of rank for nonlinear functions A Jacot
arXiv preprint arXiv:2209.15055, 2022
33 2022 The asymptotic spectrum of the hessian of dnn throughout training A Jacot, F Gabriel, C Hongler
arXiv preprint arXiv:1910.02875, 2019
32 2019 Freeze and chaos: Ntk views on dnn normalization, checkerboard and boundary artifacts A Jacot, F Gabriel, F Ged, C Hongler
Mathematical and Scientific Machine Learning, 257-270, 2022
26 * 2022 Feature Learning in A Jacot, E Golikov, C Hongler, F Gabriel
Advances in Neural Information Processing Systems 35, 6763-6774, 2022
17 2022 Bottleneck structure in learned features: Low-dimension vs regularity tradeoff A Jacot
Advances in Neural Information Processing Systems 36, 23607-23629, 2023
14 2023 Implicit bias of SGD in Z Wang, A Jacot
arXiv preprint arXiv:2305.16038, 2023
13 2023 DNN-based topology optimisation: Spatial invariance and neural tangent kernel B Dupuis, A Jacot
Advances in Neural Information Processing Systems 34, 27659-27669, 2021
7 2021 Order and chaos: NTK views on DNN normalization, checkerboard and boundary artifacts A Jacot, F Gabriel, F Ged, C Hongler
arXiv preprint arXiv:1907.05715, 2019
7 2019 Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning Y Wen, A Jacot
arXiv preprint arXiv:2402.08010, 2024
5 2024 Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes Z Tu, S Aranguri, A Jacot
arXiv preprint arXiv:2405.17580, 2024
4 2024 Understanding Layer-wise Contributions in Deep Neural Networks through Spectral Analysis Y Dandi, A Jacot
arXiv preprint arXiv:2111.03972, 2021
3 2021 Wide neural networks trained with weight decay provably exhibit neural collapse A Jacot, P Súkeník, Z Wang, M Mondelli
arXiv preprint arXiv:2410.04887, 2024
2 2024 Shallow diffusion networks provably learn hidden low-dimensional structure NM Boffi, A Jacot, S Tu, I Ziemann
arXiv preprint arXiv:2410.11275, 2024
1 2024 
Clément HonglerInstitute of Mathematics, EPFLAdresse e-mail validée de epfl.ch
