| Transfusion: Understanding transfer learning for medical imaging M Raghu, C Zhang, J Kleinberg, S Bengio Advances in neural information processing systems 32, 2019 | 1386 | 2019 |
| Do vision transformers see like convolutional neural networks? M Raghu, T Unterthiner, S Kornblith, C Zhang, A Dosovitskiy Advances in Neural Information Processing Systems 34, 2021 | 1090 | 2021 |
| On the expressive power of deep neural networks M Raghu, B Poole, J Kleinberg, S Ganguli, J Sohl-Dickstein international conference on machine learning, 2847-2854, 2017 | 1007 | 2017 |
| Rapid learning or feature reuse? towards understanding the effectiveness of maml A Raghu, M Raghu, S Bengio, O Vinyals arXiv preprint arXiv:1909.09157, 2019 | 766 | 2019 |
| Svcca: Singular vector canonical correlation analysis for deep learning dynamics and interpretability M Raghu, J Gilmer, J Yosinski, J Sohl-Dickstein Advances in neural information processing systems 30, 2017 | 744 | 2017 |
| Exponential expressivity in deep neural networks through transient chaos B Poole, S Lahiri, M Raghu, J Sohl-Dickstein, S Ganguli Advances in neural information processing systems 29, 2016 | 680 | 2016 |
| Insights on representational similarity in neural networks with canonical correlation A Morcos, M Raghu, S Bengio Advances in Neural Information Processing Systems 31, 2018 | 459 | 2018 |
| Adversarial spheres J Gilmer, L Metz, F Faghri, SS Schoenholz, M Raghu, M Wattenberg, ... arXiv preprint arXiv:1801.02774, 2018 | 456* | 2018 |
| Do wide and deep networks learn the same things? uncovering how neural network representations vary with width and depth T Nguyen, M Raghu, S Kornblith arXiv preprint arXiv:2010.15327, 2020 | 286 | 2020 |
| A survey of deep learning for scientific discovery M Raghu, E Schmidt arXiv preprint arXiv:2003.11755, 2020 | 195 | 2020 |
| Anatomy of catastrophic forgetting: Hidden representations and task semantics VV Ramasesh, E Dyer, M Raghu arXiv preprint arXiv:2007.07400, 2020 | 187 | 2020 |
| Direct uncertainty prediction for medical second opinions M Raghu, K Blumer, R Sayres, Z Obermeyer, B Kleinberg, S Mullainathan, ... International Conference on Machine Learning, 5281-5290, 2019 | 159 | 2019 |
| The algorithmic automation problem: Prediction, triage, and human effort M Raghu, K Blumer, G Corrado, J Kleinberg, Z Obermeyer, ... arXiv preprint arXiv:1903.12220, 2019 | 153 | 2019 |
| Team performance with test scores J Kleinberg, M Raghu ACM Transactions on Economics and Computation (TEAC) 6 (3-4), 1-26, 2018 | 51 | 2018 |
| Can deep reinforcement learning solve Erdos-Selfridge-Spencer games? M Raghu, A Irpan, J Andreas, B Kleinberg, Q Le, J Kleinberg International Conference on Machine Learning, 4238-4246, 2018 | 39 | 2018 |
| Teaching with commentaries A Raghu, M Raghu, S Kornblith, D Duvenaud, G Hinton arXiv preprint arXiv:2011.03037, 2020 | 31 | 2020 |
| Pointer Value Retrieval: A new benchmark for understanding the limits of neural network generalization C Zhang, M Raghu, J Kleinberg, S Bengio arXiv preprint arXiv:2107.12580, 2021 | 27 | 2021 |
| Linear additive markov processes R Kumar, M Raghu, T Sarlós, A Tomkins Proceedings of the 26th international conference on World Wide Web, 411-419, 2017 | 15 | 2017 |
| Learning to reason with neural networks: Generalization, unseen data and boolean measures E Abbe, S Bengio, E Cornacchia, J Kleinberg, A Lotfi, M Raghu, C Zhang Advances in Neural Information Processing Systems 35, 2709-2722, 2022 | 13 | 2022 |
| On the Origins of the Block Structure Phenomenon in Neural Network Representations T Nguyen, M Raghu, S Kornblith arXiv preprint arXiv:2202.07184, 2022 | 12 | 2022 |
