Spider: Near-optimal non-convex optimization via stochastic path-integrated differential estimator C Fang, CJ Li, Z Lin, T Zhang Advances in Neural Information Processing Systems 31, 2018 | 452 | 2018 |

Sharp analysis for nonconvex sgd escaping from saddle points C Fang, Z Lin, T Zhang Conference on Learning Theory, 1192-1234, 2019 | 84 | 2019 |

Exploring deep neural networks via layer-peeled model: Minority collapse in imbalanced training C Fang, H He, Q Long, WJ Su Proceedings of the National Academy of Sciences 118 (43), e2103091118, 2021 | 49 | 2021 |

Modeling from features: a mean-field framework for over-parameterized deep neural networks C Fang, J Lee, P Yang, T Zhang Conference on learning theory, 1887-1936, 2021 | 41 | 2021 |

Accelerated optimization for machine learning Z Lin, H Li, C Fang Nature Singapore: Springer, 2020 | 40 | 2020 |

A sharp convergence rate analysis for distributed accelerated gradient methods H Li, C Fang, W Yin, Z Lin arXiv preprint arXiv:1810.01053, 2018 | 35 | 2018 |

Decentralized accelerated gradient methods with increasing penalty parameters H Li, C Fang, W Yin, Z Lin IEEE transactions on Signal Processing 68, 4855-4870, 2020 | 32 | 2020 |

Complexities in projection-free stochastic non-convex minimization Z Shen, C Fang, P Zhao, J Huang, H Qian The 22nd International Conference on Artificial Intelligence and Statistics …, 2019 | 31 | 2019 |

A robust hybrid method for text detection in natural scenes by learning-based partial differential equations Z Zhao, C Fang, Z Lin, Y Wu Neurocomputing 168, 23-34, 2015 | 31 | 2015 |

Feature learning via partial differential equation with applications to face recognition C Fang, Z Zhao, P Zhou, Z Lin Pattern Recognition 69, 14-25, 2017 | 28 | 2017 |

Lifted proximal operator machines J Li, C Fang, Z Lin Proceedings of the AAAI Conference on Artificial Intelligence 33 (01), 4181-4188, 2019 | 26 | 2019 |

Hessian-aware zeroth-order optimization for black-box adversarial attack H Ye, Z Huang, C Fang, CJ Li, T Zhang arXiv preprint arXiv:1812.11377, 2018 | 26 | 2018 |

Dictionary learning with structured noise P Zhou, C Fang, Z Lin, C Zhang, EY Chang Neurocomputing 273, 414-423, 2018 | 26 | 2018 |

Accelerated first-order optimization algorithms for machine learning H Li, C Fang, Z Lin Proceedings of the IEEE 108 (11), 2067-2082, 2020 | 20 | 2020 |

Improved analysis of clipping algorithms for non-convex optimization B Zhang, J Jin, C Fang, L Wang Advances in Neural Information Processing Systems 33, 15511-15521, 2020 | 20 | 2020 |

Mathematical models of overparameterized neural networks C Fang, H Dong, T Zhang Proceedings of the IEEE 109 (5), 683-703, 2021 | 16 | 2021 |

Convex formulation of overparameterized deep neural networks C Fang, Y Gu, W Zhang, T Zhang IEEE Transactions on Information Theory 68 (8), 5340-5352, 2022 | 13 | 2022 |

Layer-peeled model: Toward understanding well-trained deep neural networks C Fang, H He, Q Long, WJ Su arXiv preprint arXiv:2101.12699 4, 2021 | 13 | 2021 |

Training neural networks by lifted proximal operator machines J Li, M Xiao, C Fang, Y Dai, C Xu, Z Lin IEEE Transactions on Pattern Analysis and Machine Intelligence 44 (6), 3334-3348, 2020 | 13 | 2020 |

Over parameterized two-level neural networks can learn near optimal feature representations C Fang, H Dong, T Zhang arXiv preprint arXiv:1910.11508, 2019 | 13 | 2019 |