| Why are adaptive methods good for attention models? J Zhang, SP Karimireddy, A Veit, S Kim, S Reddi, S Kumar, S Sra Advances in Neural Information Processing Systems 33, 15383-15393, 2020 | 357* | 2020 |
| Local low-rank matrix approximation J Lee, S Kim, G Lebanon, Y Singer International conference on machine learning, 82-90, 2013 | 261 | 2013 |
| Local collaborative ranking J Lee, S Bengio, S Kim, G Lebanon, Y Singer Proceedings of the 23rd international conference on World wide web, 85-96, 2014 | 160 | 2014 |
| A statistical perspective on distillation AK Menon, AS Rawat, S Reddi, S Kim, S Kumar International Conference on Machine Learning, 7632-7642, 2021 | 127* | 2021 |
| LLORMA: Local low-rank matrix approximation J Lee, S Kim, G Lebanon, Y Singer, S Bengio Journal of Machine Learning Research 17 (15), 1-24, 2016 | 127 | 2016 |
| ConceptVector: Text visual analytics via interactive lexicon building using word embedding D Park, S Kim, J Lee, J Choo, N Diakopoulos, N Elmqvist IEEE transactions on visualization and computer graphics 24 (1), 361-370, 2017 | 110 | 2017 |
| Evaluations and methods for explanation through robustness analysis CY Hsieh, CK Yeh, X Liu, P Ravikumar, S Kim, S Kumar, CJ Hsieh arXiv preprint arXiv:2006.00442, 2020 | 65 | 2020 |
| On the reproducibility of neural network predictions S Bhojanapalli, K Wilber, A Veit, AS Rawat, S Kim, A Menon, S Kumar arXiv preprint arXiv:2102.03349, 2021 | 41 | 2021 |
| Beyond sentiment: The manifold of human emotions S Kim, F Li, G Lebanon, I Essa Artificial Intelligence and Statistics, 360-369, 2013 | 38 | 2013 |
| Rankdistil: Knowledge distillation for ranking S Reddi, RK Pasumarthi, A Menon, AS Rawat, F Yu, S Kim, A Veit, ... International Conference on Artificial Intelligence and Statistics, 2368-2376, 2021 | 34 | 2021 |
| In defense of dual-encoders for neural ranking A Menon, S Jayasumana, AS Rawat, S Kim, S Reddi, S Kumar International Conference on Machine Learning, 15376-15400, 2022 | 27 | 2022 |
| Semantic label smoothing for sequence to sequence problems M Lukasik, H Jain, AK Menon, S Kim, S Bhojanapalli, F Yu, S Kumar arXiv preprint arXiv:2010.07447, 2020 | 21 | 2020 |
| Automatic feature induction for stagewise collaborative filtering J Lee, M Sun, S Kim, G Lebanon Advances in Neural Information Processing Systems 25, 2012 | 17 | 2012 |
| Supervision complexity and its role in knowledge distillation H Harutyunyan, AS Rawat, AK Menon, S Kim, S Kumar arXiv preprint arXiv:2301.12245, 2023 | 14 | 2023 |
| Efficient training of language models using few-shot learning SJ Reddi, S Miryoosefi, S Karp, S Krishnan, S Kale, S Kim, S Kumar International Conference on Machine Learning, 14553-14568, 2023 | 11 | 2023 |
| Matrix approximation under local low-rank assumption J Lee, S Kim, G Lebanon, Y Singer arXiv preprint arXiv:1301.3192, 2013 | 9 | 2013 |
| Embeddistill: A geometric knowledge distillation for information retrieval S Kim, AS Rawat, M Zaheer, S Jayasumana, V Sadhanala, W Jitkrittum, ... arXiv preprint arXiv:2301.12005, 2023 | 6 | 2023 |
| Local context sparse coding S Kim, J Lee, G Lebanon, H Park Proceedings of the AAAI Conference on Artificial Intelligence 29 (1), 2015 | 5 | 2015 |
| Estimating temporal dynamics of human emotions S Kim, J Lee, G Lebanon, H Park Proceedings of the AAAI Conference on Artificial Intelligence 29 (1), 2015 | 5 | 2015 |
| Fast spammer detection using structural rank S Kim, H Park, G Lebanon arXiv preprint arXiv:1407.7072, 2014 | 4 | 2014 |
Sanjiv KumarGoogle Fellow, VP, Google Research在 google.com 的电子邮件经过验证
