| Exploring generalization in deep learning B Neyshabur, S Bhojanapalli, D McAllester, N Srebro Advances in neural information processing systems 30, 2017 | 1054 | 2017 |
| Large batch optimization for deep learning: Training bert in 76 minutes Y You, J Li, S Reddi, J Hseu, S Kumar, S Bhojanapalli, X Song, J Demmel, ... arXiv preprint arXiv:1904.00962, 2019 | 642 | 2019 |
| A pac-bayesian approach to spectrally-normalized margin bounds for neural networks B Neyshabur, S Bhojanapalli, N Srebro arXiv preprint arXiv:1707.09564, 2017 | 524 | 2017 |
| Towards understanding the role of over-parametrization in generalization of neural networks B Neyshabur, Z Li, S Bhojanapalli, Y LeCun, N Srebro arXiv preprint arXiv:1805.12076, 2018 | 494 | 2018 |
| Global optimality of local search for low rank matrix recovery S Bhojanapalli, B Neyshabur, N Srebro Advances in Neural Information Processing Systems, 3873-3881, 2016 | 392 | 2016 |
| Implicit regularization in matrix factorization S Gunasekar, BE Woodworth, S Bhojanapalli, B Neyshabur, N Srebro Advances in Neural Information Processing Systems 30, 2017 | 372 | 2017 |
| Does label smoothing mitigate label noise? M Lukasik, S Bhojanapalli, A Menon, S Kumar International Conference on Machine Learning, 6448-6458, 2020 | 212 | 2020 |
| Understanding robustness of transformers for image classification S Bhojanapalli, A Chakrabarti, D Glasner, D Li, T Unterthiner, A Veit Proceedings of the IEEE/CVF international conference on computer vision …, 2021 | 202 | 2021 |
| Dropping convexity for faster semi-definite optimization S Bhojanapalli, A Kyrillidis, S Sanghavi Conference on Learning Theory, 530-582, 2016 | 179 | 2016 |
| Are transformers universal approximators of sequence-to-sequence functions? C Yun, S Bhojanapalli, AS Rawat, SJ Reddi, S Kumar arXiv preprint arXiv:1912.10077, 2019 | 143 | 2019 |
| Coherent matrix completion. Y Chen, S Bhojanapalli, S Sanghavi, R Ward arXiv preprint arXiv:1306.2979, 2013 | 142 | 2013 |
| Universal matrix completion S Bhojanapalli, P Jain International Conference on Machine Learning, 1881-1889, 2014 | 109 | 2014 |
| Stabilizing GAN training with multiple random projections B Neyshabur, S Bhojanapalli, A Chakrabarti arXiv preprint arXiv:1705.07831, 2017 | 87 | 2017 |
| Completing any low-rank matrix, provably Y Chen, S Bhojanapalli, S Sanghavi, R Ward The Journal of Machine Learning Research 16 (1), 2999-3034, 2015 | 81 | 2015 |
| Low-rank bottleneck in multi-head attention models S Bhojanapalli, C Yun, AS Rawat, S Reddi, S Kumar International Conference on Machine Learning, 864-873, 2020 | 45 | 2020 |
| Tighter low-rank approximation via sampling the leveraged element S Bhojanapalli, P Jain, S Sanghavi Proceedings of the twenty-sixth annual ACM-SIAM symposium on Discrete …, 2014 | 41 | 2014 |
| Smoothed analysis for low-rank solutions to semidefinite programs in quadratic penalty form S Bhojanapalli, N Boumal, P Jain, P Netrapalli Conference On Learning Theory, 3243-3270, 2018 | 40 | 2018 |
| O (n) connections are expressive enough: Universal approximability of sparse transformers C Yun, YW Chang, S Bhojanapalli, AS Rawat, S Reddi, S Kumar Advances in Neural Information Processing Systems 33, 13783-13794, 2020 | 39 | 2020 |
| Modifying memories in transformer models C Zhu, AS Rawat, M Zaheer, S Bhojanapalli, D Li, F Yu, S Kumar arXiv preprint arXiv:2012.00363, 2020 | 35 | 2020 |
| A new sampling technique for tensors S Bhojanapalli, S Sanghavi arXiv preprint arXiv:1502.05023, 2015 | 34 | 2015 |
Behnam NeyshaburSenior Staff Research Scientist, DeepMindVerified email at google.com
