| Exploring generalization in deep learning B Neyshabur, S Bhojanapalli, D McAllester, N Srebro Advances in Neural Information Processing Systems, 2017 | 1399 | 2017 |
| Gemini: a family of highly capable multimodal models G Team, R Anil, S Borgeaud, Y Wu, JB Alayrac, J Yu, R Soricut, ... arXiv preprint arXiv:2312.11805, 2023 | 1389 | 2023 |
| Sharpness-Aware Minimization for Efficiently Improving Generalization P Foret, A Kleiner, H Mobahi, B Neyshabur International Conference on Learning Representations, 2021 | 1271 | 2021 |
| Beyond the imitation game: Quantifying and extrapolating the capabilities of language models A Srivastava, A Rastogi, A Rao, AAM Shoeb, A Abid, A Fisch, AR Brown, ... Transactions on Machine Learning Research, 2023 | 983 | 2023 |
| In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning B Neyshabur, R Tomioka, N Srebro International Conference on Learning Representations, 2015 | 715 | 2015 |
| Stronger generalization bounds for deep nets via a compression approach S Arora, R Ge, B Neyshabur, Y Zhang The 35th International Conference on Machine Learning, 2018 | 691 | 2018 |
| A pac-bayesian approach to spectrally-normalized margin bounds for neural networks B Neyshabur, S Bhojanapalli, N Srebro International Conference on Learning Representations, 2018 | 660 | 2018 |
| Norm-Based Capacity Control in Neural Networks B Neyshabur, R Tomioka, N Srebro Conference on Learning Theory, 1376–1401, 2015 | 642 | 2015 |
| Fantastic Generalization Measures and Where to Find Them Y Jiang, B Neyshabur, H Mobahi, D Krishnan, S Bengio International Conference on Learning Representations, 2020 | 625 | 2020 |
| Towards understanding the role of over-parametrization in generalization of neural networks B Neyshabur, Z Li, S Bhojanapalli, Y LeCun, N Srebro International Conference on Learning Representations, 2019 | 601 | 2019 |
| Implicit regularization in matrix factorization S Gunasekar, BE Woodworth, S Bhojanapalli, B Neyshabur, N Srebro Advances in neural information processing systems 30, 2017 | 533 | 2017 |
| Solving quantitative reasoning problems with language models A Lewkowycz, A Andreassen, D Dohan, E Dyer, H Michalewski, ... Advances in Neural Information Processing Systems, 2022 | 509 | 2022 |
| What is being transferred in transfer learning? B Neyshabur, H Sedghi, C Zhang Advances in Neural Information Processing Systems, 2020 | 485 | 2020 |
| Global Optimality of Local Search for Low Rank Matrix Recovery S Bhojanapalli, B Neyshabur, N Srebro Advances in Neural Information Processing Systems, 2016 | 444 | 2016 |
| Predicting protein–protein interactions through sequence-based deep learning S Hashemifar, B Neyshabur, AA Khan, J Xu Bioinformatics 34 (17), i802-i810, 2018 | 337 | 2018 |
| Path-SGD: Path-Normalized Optimization in Deep Neural Networks B Neyshabur, RR Salakhutdinov, N Srebro Advances in Neural Information Processing Systems, 2413-2421, 2015 | 328 | 2015 |
| Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context M Reid, N Savinov, D Teplyashin, D Lepikhin, T Lillicrap, J Alayrac, ... arXiv preprint arXiv:2403.05530, 2024 | 307 | 2024 |
| On Symmetric and Asymmetric LSHs for Inner Product Search B Neyshabur, N Srebro The 32nd International Conference on Machine Learning, 1926–1934, 2015 | 221 | 2015 |
| NETAL: a new graph-based method for global alignment of protein–protein interaction networks B Neyshabur, A Khadem, S Hashemifar, SS Arab Bioinformatics 29 (13), 1654-1662, 2013 | 210 | 2013 |
| Corralling a band of bandit algorithms A Agarwal, H Luo, B Neyshabur, RE Schapire Conference on Learning Theory, 2017 | 184 | 2017 |
Nathan SrebroProfessor, TTIC and University of ChicagoVerified email at ttic.edu
