Arthur Jacot

发表

Neural tangent kernel: convergence and generalization in neural networks (invited paper)

Arthur Jacot, Franck Gabriel, Cl'ement Hongler, 2018, NeurIPS.

Disentangling feature and lazy training in deep neural networks

M. Wyart, Arthur Jacot, M. Geiger, 2019, Journal of Statistical Mechanics: Theory and Experiment.

Scaling description of generalization with number of parameters in deep learning pdf

Levent Sagun, Matthieu Wyart, Giulio Biroli, 2019, Journal of Statistical Mechanics: Theory and Experiment.

Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions

Arthur Jacot, 2022, ArXiv.

Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances pdf

Wulfram Gerstner, Johanni Brea, Arthur Jacot, 2021, ICML.

Freeze and Chaos: NTK views on DNN Normalization, Checkerboard and Boundary Artifacts

Arthur Jacot, Franck Gabriel, C. Hongler, 2022, MSML.

DNN-Based Topology Optimisation: Spatial Invariance and Neural Tangent Kernel pdf

Arthur Jacot, Benjamin Dupuis, Arthur Jacot, 2021, NeurIPS.

Disentangling feature and lazy training in deep neural networks

Matthieu Wyart, Mario Geiger, Stefano Spigler, 2019, Journal of Statistical Mechanics: Theory and Experiment.

Kernel Alignment Risk Estimator: Risk Prediction from Training Data pdf

Arthur Jacot, Franck Gabriel, Cl'ement Hongler, 2020, NeurIPS.

Implicit Regularization of Random Feature Models pdf

Arthur Jacot, Franck Gabriel, Clément Hongler, 2020, ICML.

The asymptotic spectrum of the Hessian of DNN throughout training

Arthur Jacot, Franck Gabriel, Clément Hongler, 2019, ICLR.

Neural Tangent Kernel: Convergence and Generalization in Neural Networks

Arthur Jacot, Franck Gabriel, Clément Hongler, 2018, NeurIPS.

Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions

Arthur Jacot, 2022, ICLR.

Feature Learning in L2-regularized DNNs: Attraction/Repulsion and Sparsity

Arthur Jacot, Franck Gabriel, Clément Hongler, 2022, NeurIPS.

Freeze and Chaos for DNNs: an NTK view of Batch Normalization, Checkerboard and Boundary Effects pdf

Arthur Jacot, Franck Gabriel, Cl'ement Hongler, 2019, ArXiv.

Disentangling feature and lazy learning in deep neural networks: an empirical study pdf

Matthieu Wyart, Mario Geiger, Stefano Spigler, 2019, ArXiv.

Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff

Arthur Jacot, 2023, arXiv.org.

Saddle-to-Saddle Dynamics in Deep Linear Networks: Small Initialization Training, Symmetry, and Sparsity

Arthur Jacot, Franck Gabriel, Clément Hongler, 2021, 2106.15933.

Implicit bias of SGD in L2-regularized linear DNNs: One-way jumps from high to low rank

Arthur Jacot, Zihan Wang, 2023, ArXiv.

Deep Linear Networks Dynamics: Low-Rank Biases Induced by Initialization Scale and L2 Regularization pdf

Arthur Jacot, Franck Gabriel, Franccois Ged, 2021, ArXiv.

Neural tangent kernel: convergence and generalization in neural networks (invited paper)

Arthur Jacot, Franck Gabriel, C. Hongler, 2021, STOC.

Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff

Arthur Jacot, 2023, Neural Information Processing Systems.

Freeze and Chaos: NTK views on DNN Normalization, Checkerboard and Boundary Artifacts

Arthur Jacot, Franck Gabriel, Clément Hongler, 2022, Mathematical and Scientific Machine Learning.

Hamiltonian Mechanics of Feature Learning: Bottleneck Structure in Leaky ResNets

Arthur Jacot, Alexandre Kaiser, 2024, ArXiv.

Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes

Arthur Jacot, Zhenfeng Tu, Santiago Aranguri, 2024, 2405.17580.

Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning

Arthur Jacot, Yuxiao Wen, 2024, ArXiv.

Implicit bias of SGD in L2-regularized linear DNNs: One-way jumps from high to low rank

Arthur Jacot, Zihan Wang, 2023, ArXiv.