| Deep double descent: Where bigger models and more data hurt P Nakkiran, G Kaplun, Y Bansal, T Yang, B Barak, I Sutskever International Conference on Learning Representations (ICLR) 2019, 2019 | 163 | 2019 |
| Having your cake and eating it too: Jointly optimal erasure codes for i/o, storage, and network-bandwidth KV Rashmi, P Nakkiran, J Wang, NB Shah, K Ramchandran 13th {USENIX} Conference on File and Storage Technologies ({FAST} 15), 81-94, 2015 | 127 | 2015 |
| Compressing deep neural networks using a rank-constrained topology P Nakkiran, R Alvarez, R Prabhavalkar, C Parada | 75 | 2015 |
| Automatic gain control and multi-style training for robust small-footprint keyword spotting with deep neural networks R Prabhavalkar, R Alvarez, C Parada, P Nakkiran, TN Sainath 2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015 | 58 | 2015 |
| Adversarial robustness may be at odds with simplicity P Nakkiran arXiv preprint arXiv:1901.00532, 2019 | 53 | 2019 |
| SGD on Neural Networks Learns Functions of Increasing Complexity P Nakkiran, G Kaplun, D Kalimeris, T Yang, B Edelman, H Zhang, B Barak Advances in Neural Information Processing Systems, 3491-3501, 2019 | 43* | 2019 |
| Optimal regularization can mitigate double descent P Nakkiran, P Venkat, S Kakade, T Ma arXiv preprint arXiv:2003.01897, 2020 | 26 | 2020 |
| More data can hurt for linear regression: Sample-wise double descent P Nakkiran arXiv preprint arXiv:1912.07242, 2019 | 25 | 2019 |
| Computational Limitations in Robust Classification and Win-Win Results A Degwekar, P Nakkiran, V Vaikuntanathan Proceedings of the Thirty-Second Conference on Learning Theory 99, 994-1028, 2019 | 23 | 2019 |
| General strong polarization J Błasiok, V Guruswami, P Nakkiran, A Rudra, M Sudan Proceedings of the 50th Annual ACM SIGACT Symposium on Theory of Computing …, 2018 | 19 | 2018 |
| Predicting positive and negative links with noisy queries: Theory & practice CE Tsourakakis, M Mitzenmacher, KG Larsen, J Błasiok, B Lawson, ... arXiv preprint arXiv:1709.07308, 2017 | 12 | 2017 |
| A Discussion of'Adversarial Examples Are Not Bugs, They Are Features': Adversarial Examples are Just Bugs, Too P Nakkiran Distill 4 (8), e00019. 5, 2019 | 11 | 2019 |
| Fundamental limits on communication for oblivious updates in storage networks P Nakkiran, NB Shah, KV Rashmi 2014 IEEE Global Communications Conference, 2363-2368, 2014 | 9 | 2014 |
| Automatic gain control for speech recognition R Alvarez, P Nakkiran US Patent App. 14/727,741, 2016 | 7 | 2016 |
| Rank-constrained neural networks RA Guevara, P Nakkiran US Patent 9,767,410, 2017 | 4 | 2017 |
| Optimal systematic distributed storage codes with fast encoding P Nakkiran, KV Rashmi, K Ramchandran 2016 IEEE International Symposium on Information Theory (ISIT), 430-434, 2016 | 4 | 2016 |
| Optimal oblivious updates in distributed storage networks P Nakkiran, NB Shah, KV Rashmi, A Sahai, K Ramchandran Accessed: Jul, 2016 | 4 | 2016 |
| Learning rate annealing can provably help generalization, even for convex problems P Nakkiran arXiv preprint arXiv:2005.07360, 2020 | 3 | 2020 |
| Near-Optimal UGC-hardness of Approximating Max k-CSP_R P Manurangsi, P Nakkiran, L Trevisan arXiv preprint arXiv:1511.06558, 2015 | 2 | 2015 |
| Distributional Generalization: A New Kind of Generalization P Nakkiran, Y Bansal arXiv preprint arXiv:2009.08092, 2020 | 1 | 2020 |
Boaz BarakHarvard UniversityVerified email at boazbarak.org
