| Provably robust deep learning via adversarially trained smoothed classifiers H Salman, J Li, I Razenshteyn, P Zhang, H Zhang, S Bubeck, G Yang Advances in Neural Information Processing Systems, 11292-11303, 2019 | 464 | 2019 |
| Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes R Novak, L Xiao, Y Bahri, J Lee, G Yang, DA Abolafia, J Pennington, ... | 309 | 2018 |
| Scaling limits of wide neural networks with weight sharing: Gaussian process behavior, gradient independence, and neural tangent kernel derivation G Yang arXiv preprint arXiv:1902.04760, 2019 | 259 | 2019 |
| A convex relaxation barrier to tight robustness verification of neural networks H Salman, G Yang, H Zhang, CJ Hsieh, P Zhang Advances in Neural Information Processing Systems, 9835-9846, 2019 | 215 | 2019 |
| Mean Field Residual Networks: On the Edge of Chaos G Yang, S Schoenholz Advances in neural information processing systems, 7103-7114, 2017 | 189 | 2017 |
| A mean field theory of batch normalization G Yang, J Pennington, V Rao, J Sohl-Dickstein, SS Schoenholz arXiv preprint arXiv:1902.08129, 2019 | 181 | 2019 |
| Randomized smoothing of all shapes and sizes G Yang, T Duan, JE Hu, H Salman, I Razenshteyn, J Li International Conference on Machine Learning, 10693-10705, 2020 | 165 | 2020 |
| Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes G Yang Advances in Neural Information Processing Systems, 9947-9960, 2019 | 164* | 2019 |
| Tensor Programs IV: Feature Learning in Infinite-Width Neural Networks G Yang, EJ Hu International Conference on Machine Learning, 11727-11737, 2021 | 105 | 2021 |
| Tensor Programs II: Neural Tangent Kernel for Any Architecture G Yang arXiv preprint arXiv:2006.14548, 2020 | 102 | 2020 |
| Denoised Smoothing: A Provable Defense for Pretrained Classifiers H Salman, M Sun, G Yang, A Kapoor, JZ Kolter Advances in Neural Information Processing Systems 33, 2020 | 97 | 2020 |
| A Fine-Grained Spectral Perspective on Neural Networks G Yang, H Salman arXiv preprint arXiv:1907.10599, 2019 | 84 | 2019 |
| Feature Learning in Infinite-Width Neural Networks G Yang, EJ Hu arXiv preprint arXiv:2011.14522, 2020 | 69 | 2020 |
| High-dimensional asymptotics of feature learning: How one gradient step improves the representation J Ba, MA Erdogdu, T Suzuki, Z Wang, D Wu, G Yang Advances in Neural Information Processing Systems 35, 37932-37946, 2022 | 50 | 2022 |
| Tensor Programs IIb: Architectural Universality of Neural Tangent Kernel Training Dynamics G Yang, E Littwin arXiv preprint arXiv:2105.03703, 2021 | 48 | 2021 |
| Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer G Yang, EJ Hu, I Babuschkin, S Sidor, X Liu, D Farhi, N Ryder, J Pachocki, ... arXiv preprint arXiv:2203.03466, 2022 | 47 | 2022 |
| NAIL: A General Interactive Fiction Agent M Hausknecht, R Loynd, G Yang, A Swaminathan, JD Williams arXiv preprint arXiv:1902.04259, 2019 | 41 | 2019 |
| 3DB: A Framework for Debugging Computer Vision Models G Leclerc, H Salman, A Ilyas, S Vemprala, L Engstrom, V Vineet, K Xiao, ... arXiv preprint arXiv:2106.03805, 2021 | 40 | 2021 |
| Tensor Programs III: Neural Matrix Laws G Yang arXiv preprint arXiv:2009.10685, 2020 | 38 | 2020 |
| Lie access neural Turing machine G Yang arXiv preprint arXiv:1602.08671, 2016 | 22 | 2016 |
Hadi SalmanOpenAI, MITVerified email at mit.edu
