, Tensor Analysis, and Applications, vol.75, 2012.
A convergence theory for deep learning via over-parameterization, 2018. ,
Learning and generalization in overparameterized neural networks, going beyond two layers, 2018. ,
, On exact computation with an infinitely wide neural net, 2019.
Fine-grained analysis of optimization and generalization for overparameterized two-layer neural networks, 2019. ,
Optimization methods for large-scale machine learning, SIAM Review, vol.60, issue.2, pp.223-311, 2018. ,
DOI : 10.1137/16m1080173
URL : http://arxiv.org/pdf/1606.04838
, On Lipschitz maps and their flows, 2015.
A generalization theory of gradient descent for learning over-parameterized deep relu networks, 2019. ,
Learning with SGD and random features, Advances in Neural Information Processing Systems, pp.10192-10203, 2018. ,
URL : https://hal.archives-ouvertes.fr/hal-01958906
On the global convergence of gradient descent for overparameterized models using optimal transport, Advances in neural information processing systems, 2018. ,
URL : https://hal.archives-ouvertes.fr/hal-01798792
On early stopping in gradient descent learning, Constructive Approximation, vol.26, pp.289-315, 2007. ,
DOI : 10.1007/s00365-006-0663-2
, On the power and limitations of random features for understanding neural networks, 2019.
Wide residual networks, Proceedings of the British Machine Vision Conference (BMVC), vol.12, pp.87-88, 2016. ,
DOI : 10.5244/c.30.87
URL : https://hal.archives-ouvertes.fr/hal-01832503
Understanding deep learning requires rethinking generalization, International Conference on Learning Representations, 2017. ,
Training over-parameterized deep resnet is almost as easy as training a two-layer network, 2019. ,
Stochastic gradient descent optimizes over-parameterized deep ReLU networks, 2018. ,