Examples are not Enough, Learn to Criticize! Criticism for Interpretability B Kim, R Khanna, O Koyejo Advances in Neural Information Processing Systems 29 (NIPS 2016) 29, 2280--2288, 2016 | 137 | 2016 |

Examples are not enough, learn to criticize! criticism for interpretability B Kim, R Khanna, OO Koyejo Advances in Neural Information Processing Systems, 2280-2288, 2016 | 137 | 2016 |

Structured learning for non-smooth ranking losses S Chakrabarti, R Khanna, U Sawant, C Bhattacharyya Proceedings of the 14th ACM SIGKDD international conference on Knowledge …, 2008 | 114 | 2008 |

Estimating rates of rare events with multiple hierarchies through scalable log-linear models D Agarwal, R Agrawal, R Khanna, N Kota Proceedings of the 16th ACM SIGKDD international conference on Knowledge …, 2010 | 95 | 2010 |

Scalable greedy feature selection via weak submodularity R Khanna, E Elenberg, AG Dimakis, S Negahban, J Ghosh arXiv preprint arXiv:1703.02723, 2017 | 36 | 2017 |

Restricted strong convexity implies weak submodularity ER Elenberg, R Khanna, AG Dimakis, S Negahban arXiv preprint arXiv:1612.00804, 2016 | 31 | 2016 |

A unified optimization view on generalized matching pursuit and frank-wolfe F Locatello, R Khanna, M Tschannen, M Jaggi arXiv preprint arXiv:1702.06457, 2017 | 30 | 2017 |

Restricted strong convexity implies weak submodularity ER Elenberg, R Khanna, AG Dimakis, S Negahban The Annals of Statistics 46 (6B), 3539-3568, 2018 | 26 | 2018 |

Translating relevance scores to probabilities for contextual advertising D Agarwal, E Gabrilovich, R Hall, V Josifovski, R Khanna Proceedings of the 18th ACM conference on Information and knowledge …, 2009 | 19 | 2009 |

Sparse submodular probabilistic PCA R Khanna, J Ghosh, R Poldrack, O Koyejo Artificial Intelligence and Statistics, 453-461, 2015 | 18 | 2015 |

On approximation guarantees for greedy low rank optimization R Khanna, ER Elenberg, AG Dimakis, J Ghosh, S Negahban Proceedings of the 34th International Conference on Machine Learning-Volume …, 2017 | 16 | 2017 |

IHT dies hard: Provable accelerated iterative hard thresholding R Khanna, A Kyrillidis arXiv preprint arXiv:1712.09379, 2017 | 13 | 2017 |

Boosting variational inference: an optimization perspective F Locatello, R Khanna, J Ghosh, G Rätsch arXiv preprint arXiv:1708.01733, 2017 | 12 | 2017 |

On prior distributions and approximate inference for structured variables OO Koyejo, R Khanna, J Ghosh, R Poldrack Advances in Neural Information Processing Systems, 676-684, 2014 | 12 | 2014 |

Parallel matrix factorization for binary response R Khanna, L Zhang, D Agarwal, BC Chen 2013 IEEE International Conference on Big Data, 430-438, 2013 | 11 | 2013 |

Interpreting black box predictions using fisher kernels R Khanna, B Kim, J Ghosh, O Koyejo arXiv preprint arXiv:1810.10118, 2018 | 10 | 2018 |

Boosting black box variational inference F Locatello, G Dresdner, R Khanna, I Valera, G Rätsch Advances in Neural Information Processing Systems, 3401-3411, 2018 | 10 | 2018 |

Towards a better understanding of predict and count models SS Keerthi, T Schnabel, R Khanna arXiv preprint arXiv:1511.02024, 2015 | 7 | 2015 |

A deflation method for structured probabilistic PCA R Khanna, J Ghosh, R Poldrack, O Koyejo Proceedings of the 2017 SIAM International Conference on Data Mining, 534-542, 2017 | 3 | 2017 |

Co-regularized Monotone Retargeting for Semi-supervised LeTOR S Joshi, R Khanna, J Ghosh Proceedings of the 2018 SIAM International Conference on Data Mining, 432-440, 2018 | 1 | 2018 |