Tensor decompositions for learning latent variable models. A Anandkumar, R Ge, DJ Hsu, SM Kakade, M Telgarsky J. Mach. Learn. Res. 15 (1), 2773-2832, 2014 | 1329 | 2014 |

Escaping from saddle points—online stochastic gradient for tensor decomposition R Ge, F Huang, C Jin, Y Yuan Conference on learning theory, 797-842, 2015 | 1226 | 2015 |

How to escape saddle points efficiently C Jin, R Ge, P Netrapalli, SM Kakade, MI Jordan International conference on machine learning, 1724-1732, 2017 | 948 | 2017 |

Generalization and equilibrium in generative adversarial nets (gans) S Arora, R Ge, Y Liang, T Ma, Y Zhang International conference on machine learning, 224-232, 2017 | 787 | 2017 |

Matrix completion has no spurious local minimum R Ge, JD Lee, T Ma Advances in neural information processing systems 29, 2016 | 707 | 2016 |

Global convergence of policy gradient methods for the linear quadratic regulator M Fazel, R Ge, S Kakade, M Mesbahi International conference on machine learning, 1467-1476, 2018 | 685 | 2018 |

Stronger generalization bounds for deep nets via a compression approach S Arora, R Ge, B Neyshabur, Y Zhang International Conference on Machine Learning, 254-263, 2018 | 670 | 2018 |

A practical algorithm for topic modeling with provable guarantees S Arora, R Ge, Y Halpern, D Mimno, A Moitra, D Sontag, Y Wu, M Zhu International conference on machine learning, 280-288, 2013 | 557 | 2013 |

Learning topic models--going beyond SVD S Arora, R Ge, A Moitra 2012 IEEE 53rd annual symposium on foundations of computer science, 1-10, 2012 | 542 | 2012 |

Computing a nonnegative matrix factorization--provably S Arora, R Ge, R Kannan, A Moitra Proceedings of the forty-fourth annual ACM symposium on Theory of computing …, 2012 | 501 | 2012 |

No spurious local minima in nonconvex low rank problems: A unified geometric analysis R Ge, C Jin, Y Zheng International Conference on Machine Learning, 1233-1242, 2017 | 488 | 2017 |

Provable bounds for learning some deep representations S Arora, A Bhaskara, R Ge, T Ma International conference on machine learning, 584-592, 2014 | 446 | 2014 |

New algorithms for learning in presence of errors S Arora, R Ge Automata, Languages and Programming, 403-415, 2011 | 353 | 2011 |

Learning one-hidden-layer neural networks with landscape design R Ge, JD Lee, T Ma arXiv preprint arXiv:1711.00501, 2017 | 297 | 2017 |

New algorithms for learning incoherent and overcomplete dictionaries S Arora, R Ge, A Moitra Conference on Learning Theory, 779-806, 2014 | 233 | 2014 |

Simple, efficient, and neural algorithms for sparse coding S Arora, R Ge, T Ma, A Moitra Conference on learning theory, 113-149, 2015 | 223 | 2015 |

Computational complexity and information asymmetry in financial products S Arora, B Barak, M Brunnermeier, R Ge Communications of the ACM 54 (5), 101-107, 2011 | 217 | 2011 |

A tensor approach to learning mixed membership community models A Anandkumar, R Ge, D Hsu, SM Kakade The Journal of Machine Learning Research 15 (1), 2239-2312, 2014 | 176 | 2014 |

On nonconvex optimization for machine learning: Gradients, stochasticity, and saddle points C Jin, P Netrapalli, R Ge, SM Kakade, MI Jordan Journal of the ACM (JACM) 68 (2), 1-29, 2021 | 171 | 2021 |

The step decay schedule: A near optimal, geometrically decaying learning rate procedure for least squares R Ge, SM Kakade, R Kidambi, P Netrapalli Advances in neural information processing systems 32, 2019 | 171 | 2019 |