Robust statistical learning with Lipschitz and convex loss functions G Chinot, G Lecué, M Lerasle Probability Theory and related fields 176 (3), 897-940, 2020 | 45* | 2020 |
Gradient descent can learn less over-parameterized two-layer neural networks on classification problems A Nitanda, G Chinot, T Suzuki arXiv preprint arXiv:1905.09870, 2019 | 44* | 2019 |
On the robustness of the minimum interpolator G Chinot, M Lerasle arXiv preprint arXiv:2003.05838, 2020 | 26* | 2020 |
On the robustness of minimum-norm interpolators G Chinot, M Löffler, S van de Geer arXiv preprint arXiv:2012.00807 8, 15, 2020 | 25* | 2020 |
Robust high dimensional learning for Lipschitz and convex losses C Geoffrey, L Guillaume, L Matthieu Journal of Machine Learning Research 21 (233), 1-47, 2020 | 16 | 2020 |
ERM and RERM are optimal estimators for regression problems when malicious outliers corrupt the labels G Chinot arXiv preprint arXiv:1910.10923, 2019 | 9 | 2019 |
AdaBoost and robust one-bit compressed sensing G Chinot, F Kuchelmeister, M Löffler, S van de Geer Mathematical Statistics and Learning 5 (1), 117-158, 2022 | 5 | 2022 |
Robust learning and complexity dependent bounds for regularized problems G Chinot arXiv preprint arXiv:1902.02238, 2019 | 3 | 2019 |
Localization methods with applications to robust learning and interpolation G Chinot Institut polytechnique de Paris, 2020 | | 2020 |