Gradient descent optimizes over-parameterized deep ReLU networks D Zou, Y Cao, D Zhou, Q Gu Machine learning 109, 467-492, 2020 | 315 | 2020 |

Stochastic gradient descent optimizes over-parameterized deep relu networks D Zou, Y Cao, D Zhou, Q Gu arXiv preprint arXiv:1811.08888, 2018 | 299 | 2018 |

Generalization bounds of stochastic gradient descent for wide and deep neural networks Y Cao, Q Gu Advances in neural information processing systems 32, 2019 | 293 | 2019 |

Generalization error bounds of gradient descent for learning over-parameterized deep relu networks Y Cao, Q Gu Proceedings of the AAAI Conference on Artificial Intelligence 34 (04), 3349-3356, 2020 | 155* | 2020 |

Closing the generalization gap of adaptive gradient methods in training deep neural networks J Chen, D Zhou, Y Tang, Z Yang, Y Cao, Q Gu arXiv preprint arXiv:1806.06763, 2018 | 154 | 2018 |

On the convergence of adaptive gradient methods for nonconvex optimization D Zhou, J Chen, Y Cao, Y Tang, Z Yang, Q Gu arXiv preprint arXiv:1808.05671, 2018 | 140 | 2018 |

Towards understanding the spectral bias of deep learning Y Cao, Z Fang, Y Wu, DX Zhou, Q Gu arXiv preprint arXiv:1912.01198, 2019 | 115 | 2019 |

How much over-parameterization is sufficient to learn deep relu networks? Z Chen, Y Cao, D Zou, Q Gu arXiv preprint arXiv:1911.12360, 2019 | 104 | 2019 |

A generalized neural tangent kernel analysis for two-layer neural networks Z Chen, Y Cao, Q Gu, T Zhang Advances in Neural Information Processing Systems 33, 13363-13373, 2020 | 52* | 2020 |

Risk bounds for over-parameterized maximum margin classification on sub-gaussian mixtures Y Cao, Q Gu, M Belkin Advances in Neural Information Processing Systems 34, 8407-8418, 2021 | 39 | 2021 |

Agnostic learning of a single neuron with gradient descent S Frei, Y Cao, Q Gu Advances in Neural Information Processing Systems 33, 5417-5428, 2020 | 34 | 2020 |

Local and global inference for high dimensional nonparanormal graphical models Q Gu, Y Cao, Y Ning, H Liu arXiv preprint arXiv:1502.02347, 2015 | 34* | 2015 |

Algorithm-dependent generalization bounds for overparameterized deep residual networks S Frei, Y Cao, Q Gu Advances in neural information processing systems 32, 2019 | 31 | 2019 |

Benign overfitting in two-layer convolutional neural networks Y Cao, Z Chen, M Belkin, Q Gu Advances in neural information processing systems 35, 25237-25250, 2022 | 29 | 2022 |

Tight sample complexity of learning one-hidden-layer convolutional neural networks Y Cao, Q Gu Advances in Neural Information Processing Systems 32, 2019 | 20 | 2019 |

Understanding the generalization of adam in learning neural networks with proper regularization D Zou, Y Cao, Y Li, Q Gu arXiv preprint arXiv:2108.11371, 2021 | 19 | 2021 |

Provable generalization of sgd-trained neural networks of any width in the presence of adversarial label noise S Frei, Y Cao, Q Gu International Conference on Machine Learning, 3427-3438, 2021 | 15 | 2021 |

Agnostic learning of halfspaces with gradient descent via soft margins S Frei, Y Cao, Q Gu International Conference on Machine Learning, 3417-3426, 2021 | 12 | 2021 |

The edge density barrier: Computational-statistical tradeoffs in combinatorial inference H Lu, Y Cao, Z Yang, J Lu, H Liu, Z Wang International Conference on Machine Learning, 3247-3256, 2018 | 8 | 2018 |

High-temperature structure detection in ferromagnets Y Cao, M Neykov, H Liu Information and Inference: A Journal of the IMA 11 (1), 55-102, 2022 | 7 | 2022 |