Backward feature correction: How deep learning performs deep learning, 2020. ,
A convergence theory for deep learning via over-parameterization, Proceedings of the International Conference on Machine Learning (ICML), 2019. ,
Spherical harmonics and approximations on the unit sphere: an introduction, vol.2044, 2012. ,
Sharp estimates for eigenvalues of integral operators generated by dot product kernels on the sphere, Journal of Approximation Theory, vol.177, pp.57-68, 2014. ,
Sharp analysis of low-rank kernel matrix approximations, Conference on Learning Theory (COLT), 2013. ,
URL : https://hal.archives-ouvertes.fr/hal-00723365
Breaking the curse of dimensionality with convex neural networks, Journal of Machine Learning Research (JMLR), vol.18, issue.1, pp.629-681, 2017. ,
URL : https://hal.archives-ouvertes.fr/hal-01098505
On the equivalence between kernel quadrature rules and random feature expansions, Journal of Machine Learning Research (JMLR), vol.18, issue.1, pp.714-751, 2017. ,
URL : https://hal.archives-ouvertes.fr/hal-01118276
The convergence rate of neural networks for learned functions of different frequencies, Advances in Neural Information Processing Systems (NeurIPS), 2019. ,
Frequency bias in neural networks for input of non-uniform density, Proceedings of the International Conference on Machine Learning (ICML), p.2020 ,
To understand deep learning we need to understand kernel learning, Proceedings of the International Conference on Machine Learning (ICML), 2018. ,
Group invariance, stability to deformations, and complexity of deep convolutional representations, Journal of Machine Learning Research, vol.20, issue.25, pp.1-49, 2019. ,
URL : https://hal.archives-ouvertes.fr/hal-01536004
On the inductive bias of neural tangent kernels, Advances in Neural Information Processing Systems (NeurIPS), 2019. ,
URL : https://hal.archives-ouvertes.fr/hal-02144221
Optimal rates for the regularized least-squares algorithm, Foundations of Computational Mathematics, vol.7, issue.3, pp.331-368, 2007. ,
, Deep neural tangent kernel and laplace kernel have the same rkhs, 2020.
, Towards understanding hierarchical learning: Benefits of neural representations, 2020.
On the global convergence of gradient descent for over-parameterized models using optimal transport, Advances in Neural Information Processing Systems (NeurIPS), 2018. ,
URL : https://hal.archives-ouvertes.fr/hal-01798792
On lazy training in differentiable programming, Advances in Neural Information Processing Systems (NeurIPS), 2019. ,
URL : https://hal.archives-ouvertes.fr/hal-01945578
Kernel methods for deep learning, Advances in Neural Information Processing Systems (NIPS), 2009. ,
On the mathematical foundations of learning, Bulletin of the American mathematical society, vol.39, issue.1, pp.1-49, 2002. ,
Depth separation for neural networks, Conference on Learning Theory (COLT, 2017. ,
Toward deeper understanding of neural networks: The power of initialization and a dual view on expressivity, Advances in Neural Information Processing Systems (NIPS), 2016. ,
Gradient descent finds global minima of deep neural networks, Proceedings of the International Conference on Machine Learning (ICML), 2019. ,
Gradient descent provably optimizes over-parameterized neural networks, Proceedings of the International Conference on Learning Representations (ICLR), 2019. ,
Spherical harmonics in p dimensions, 2014. ,
The spectrum of kernel random matrices, The Annals of Statistics, vol.38, issue.1, pp.1-50, 2010. ,
The power of depth for feedforward neural networks, Conference on Learning Theory (COLT), 2016. ,
, On the similarity between the laplace and neural tangent kernels, 2020.
Linearized two-layers neural networks in high dimension, 2019. ,
Delving deep into rectifiers: Surpassing human-level performance on imagenet classification, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015. ,
Multilayer feedforward networks are universal approximators, Neural networks, vol.2, issue.5, pp.359-366, 1989. ,
Classical and quantum orthogonal polynomials in one variable, vol.13, 2005. ,
Neural tangent kernel: Convergence and generalization in neural networks, Advances in Neural Information Processing Systems (NIPS), 2018. ,
URL : https://hal.archives-ouvertes.fr/hal-01824549
Deep neural networks as gaussian processes, Proceedings of the International Conference on Learning Representations (ICLR), 2018. ,
Learning overparameterized neural networks via stochastic gradient descent on structured data, Advances in Neural Information Processing Systems (NeurIPS), 2018. ,
On the risk of minimum-norm interpolants and restricted lower isometry of kernels, Conference on Learning Theory (COLT, p.2020 ,
, Gaussian process behaviour in wide deep neural networks, 2018.
A mean field view of the landscape of two-layer neural networks, Proceedings of the National Academy of Sciences, vol.115, issue.33, pp.7665-7671, 2018. ,
Deep vs. shallow networks: An approximation theory perspective, Analysis and Applications, vol.14, issue.06, pp.829-848, 2016. ,
Bayesian learning for neural networks, 1996. ,
Approximation theory of the mlp model in neural networks, Acta numerica, vol.8, pp.143-195, 1999. ,
Random features for large-scale kernel machines, Advances in Neural Information Processing Systems (NIPS), 2007. ,
Generalization properties of learning with random features, Advances in Neural Information Processing Systems, pp.3215-3225, 2017. ,
Risk bounds for multi-layer perceptrons through spectra of integral operators, 2020. ,
Nonparametric regression using deep neural networks with relu activation function, Annals of Statistics, vol.48, issue.4, pp.1875-1897, 2020. ,
Regularization with dot-product kernels, Advances in Neural Information Processing Systems (NIPS), 2001. ,
Benefits of depth in neural networks, Conference on Learning Theory (COLT), 2016. ,
Error bounds for approximations with deep relu networks, Neural Networks, vol.94, pp.103-114, 2017. ,
Stochastic gradient descent optimizes over-parameterized deep relu networks, Machine Learning, 2019. ,