| signSGD: Compressed optimisation for non-convex problems J Bernstein, YX Wang, K Azizzadenesheli, A Anandkumar International Conference on Machine Learning, 2018 | 1143 | 2018 |
| Stochastic activation pruning for robust adversarial defense GS Dhillon, K Azizzadenesheli, ZC Lipton, J Bernstein, J Kossaifi, ... International Conference on Learning Representations, 2018 | 716 | 2018 |
| signSGD with majority vote is communication efficient and fault tolerant J Bernstein, J Zhao, K Azizzadenesheli, A Anandkumar International Conference on Learning Representations, 2019 | 210 | 2019 |
| On the distance between two neural networks and the stability of learning J Bernstein, A Vahdat, Y Yue, MY Liu Advances in Neural Information Processing Systems, 2020 | 58 | 2020 |
| Learning by turning: Neural architecture aware optimisation Y Liu, J Bernstein, M Meister, Y Yue International Conference on Machine Learning, 2021 | 23 | 2021 |
| Learning compositional functions via multiplicative weight updates J Bernstein, J Zhao, M Meister, MY Liu, A Anandkumar, Y Yue Advances in Neural Information Processing Systems, 2020 | 22 | 2020 |
| A spectral condition for feature learning G Yang, JB Simon, J Bernstein arXiv:2310.17813, 2023 | 19 | 2023 |
| Automatic gradient descent: Deep learning without hyperparameters J Bernstein, C Mingard, K Huang, N Azizan, Y Yue arXiv:2304.05187, 2023 | 11 | 2023 |
| Training neural networks from scratch with parallel low-rank adapters M Huh, B Cheung, J Bernstein, P Isola, P Agrawal arXiv:2402.16828, 2024 | 7 | 2024 |
| Markov transitions between attractor states in a recurrent neural network J Bernstein, I Dasgupta, D Rolnick, H Sompolinsky AAAI Spring Symposium Series, 2017 | 7 | 2017 |
| Computing the information content of trained neural networks J Bernstein, Y Yue Workshop on the Theory of Overparameterized Machine Learning, 2021 | 6 | 2021 |
| Investigating generalization by controlling normalized margin A Farhang, J Bernstein, K Tirumala, Y Liu, Y Yue International Conference on Machine Learning, 2022 | 5 | 2022 |
| Fine-grained system identification of nonlinear neural circuits D Bagherian, J Gornet, J Bernstein, YL Ni, Y Yue, M Meister International Conference on Knowledge Discovery and Data Mining, 2021 | 5 | 2021 |
| Optimisation & generalisation in networks of neurons J Bernstein PhD thesis, California Institute of Technology, 2022 | 4 | 2022 |
| Kernel interpolation as a Bayes point machine J Bernstein, A Farhang, Y Yue arXiv:2110.04274, 2022 | 4* | 2022 |
| Scalable optimization in the modular norm T Large, Y Liu, M Huh, H Bahng, P Isola, J Bernstein Advances in Neural Information Processing Systems, 2024 | 3 | 2024 |
| Old optimizer, new norm: An anthology J Bernstein, L Newhouse Workshop on Optimization for Machine Learning, 2024 | 2 | 2024 |
| Modular duality in deep learning J Bernstein, L Newhouse arXiv:2410.21265, 2024 | | 2024 |
| Opportunities, issues, and challenges for generative AI in fostering equitable pathways in computing education C Breazeal, A Rai, B Ramesh, L Chen, Y Long, A Aria, H Loi, A Torralba, ... An MIT Exploration of Generative AI, 2024 | | 2024 |
| The neural sampling hypothesis in dynamic environments J Bernstein Part III project report, University of Cambridge, 2016 | | 2016 |
