A latent variable model approach to PMI-based word embeddings S Arora, Y Li, Y Liang, T Ma, A Risteski Transactions of the Association for Computational Linguistics 4, 385-399, 2016 | 127 | 2016 |

Linear algebraic structure of word senses, with applications to polysemy S Arora, Y Li, Y Liang, T Ma, A Risteski Transactions of the Association of Computational Linguistics 6, 483-495, 2018 | 81 | 2018 |

Random Walks on Context Spaces: Towards an Explanation of the Mysteries of Semantic Word Embeddings S Arora, Y Li, Y Liang, T Ma, A Risteski arXiv preprint arXiv:1502.03520, 2015 | 46 | 2015 |

RAND-WALK: A Latent Variable Model Approach to Word Embeddings S Arora, Y Li, Y Liang, T Ma, A Risteski arXiv preprint arXiv:1502.03520, 2015 | 43* | 2015 |

Do GANs learn the distribution? Some Theory and Empirics S Arora, A Risteski, Y Zhang | 40 | 2018 |

On the ability of neural nets to express distributions H Lee, R Ge, T Ma, A Risteski, S Arora arXiv preprint arXiv:1702.07028, 2017 | 29 | 2017 |

Recovery guarantee of weighted low-rank approximation via alternating minimization Y Li, Y Liang, A Risteski International Conference on Machine Learning, 2358-2367, 2016 | 22 | 2016 |

Provable learning of noisy-or networks S Arora, R Ge, T Ma, A Risteski Proceedings of the 49th Annual ACM SIGACT Symposium on Theory of Computing …, 2017 | 19 | 2017 |

Approximability of Discriminators Implies Diversity in GANs Y Bai, T Ma, A Risteski arXiv preprint arXiv:1806.10586, 2018 | 18 | 2018 |

On some provably correct cases of variational inference for topic models P Awasthi, A Risteski Advances in Neural Information Processing Systems, 2098-2106, 2015 | 16 | 2015 |

Automated WordNet Construction Using Word Embeddings M Khodak, A Risteski, C Fellbaum, S Arora Proceedings of the 1st Workshop on Sense, Concept and Entity Representations …, 2017 | 14 | 2017 |

Label optimal regret bounds for online local learning P Awasthi, M Charikar, KA Lai, A Risteski Conference on Learning Theory, 150-166, 2015 | 13 | 2015 |

Theoretical limitations of Encoder-Decoder GAN architectures S Arora, A Risteski, Y Zhang arXiv preprint arXiv:1711.02651, 2017 | 12 | 2017 |

Recovery guarantee of non-negative matrix factorization via alternating updates Y Li, Y Liang, A Risteski Advances in Neural Information Processing Systems, 4987-4995, 2016 | 12 | 2016 |

Beyond Log-concavity: Provable Guarantees for Sampling Multi-modal Distributions using Simulated Tempering Langevin Monte Carlo R Ge, H Lee, A Risteski arXiv preprint arXiv:1710.02736, 2017 | 11 | 2017 |

What makes a Tree a Straight Skeleton? O Aichholzer, H Cheng, SL Devadoss, T Hackl, S Huber, B Li, A Risteski CCCG, 253-258, 2012 | 11 | 2012 |

Algorithms and matching lower bounds for approximately-convex optimization A Risteski, Y Li Advances in Neural Information Processing Systems, 4745-4753, 2016 | 10 | 2016 |

Algorithms and matching lower bounds for approximately-convex optimization A Risteski, Y Li Advances in Neural Information Processing Systems, 4745-4753, 2016 | 10 | 2016 |

How to calculate partition functions using convex programming hierarchies: provable bounds for variational methods A Risteski Conference on Learning Theory, 1402-1416, 2016 | 8 | 2016 |

On Routing Disjoint Paths in Bounded Treewidth Graphs A Ene, M Mnich, M Pilipczuk, A Risteski arXiv preprint arXiv:1512.01829, 2015 | 7 | 2015 |