| Deep Neural Networks as Gaussian Processes J Lee*, Y Bahri*, R Novak, SS Schoenholz, J Pennington, ... International Conference on Learning Representations (ICLR), 2018 | 1335 | 2018 |
| 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, ... TMLR 2023, 2022 | 1175 | 2022 |
| Wide neural networks of any depth evolve as linear models under gradient descent J Lee*, L Xiao*, SS Schoenholz, Y Bahri, J Sohl-Dickstein, J Pennington Neural Information Processing Systems (NeurIPS), 2019 | 1164 | 2019 |
| Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context G Team, P Georgiev, VI Lei, R Burnell, L Bai, A Gulati, G Tanzer, ... arXiv preprint arXiv:2403.05530, 2024 | 684 | 2024 |
| Measuring the effects of data parallelism on neural network training CJ Shallue*, J Lee*, J Antognini, J Sohl-Dickstein, R Frostig, GE Dahl Journal of Machine Learning Research (2019) 20, 1-49, 2019 | 457 | 2019 |
| On empirical comparisons of optimizers for deep learning D Choi arXiv preprint arXiv:1910.05446, 2019 | 393 | 2019 |
| Bayesian Deep Convolutional Neural Networks with Many Channels are Gaussian Processes R Novak*, L Xiao*, J Lee, Y Bahri, G Yang, D Abolafia, J Pennington, ... International Conference on Learning Representations (ICLR), 2019 | 392* | 2019 |
| Neural tangents: Fast and easy infinite neural networks in python R Novak*, L Xiao*, J Hron, J Lee, AA Alemi, J Sohl-Dickstein, ... International Conference on Learning Representations (ICLR), Spotlight, 2020 | 263 | 2020 |
| Dataset Distillation with Infinitely Wide Convolutional Networks T Nguyen, R Novak, L Xiao, J Lee Neural Information Processing Systems (NeurIPS), 2021 | 251 | 2021 |
| Dataset Meta-Learning from Kernel Ridge-Regression T Nguyen, Z Chen, J Lee International Conference on Learning Representations (ICLR), 2021 | 243 | 2021 |
| Finite versus infinite neural networks: an empirical study J Lee, SS Schoenholz, J Pennington, B Adlam, L Xiao, R Novak, ... Neural Information Processing Systems (NeurIPS), Spotlight, 2020 | 227 | 2020 |
| Explaining neural scaling laws Y Bahri*, E Dyer*, J Kaplan*, J Lee*, U Sharma* arXiv preprint arXiv:2102.06701, 2021 | 215 | 2021 |
| The superconformal bootstrap in three dimensions SM Chester, J Lee, SS Pufu, R Yacoby Journal of High Energy Physics 2014 (9), 1-59, 2014 | 167 | 2014 |
| Exact correlators of BPS operators from the 3d superconformal bootstrap SM Chester, J Lee, SS Pufu, R Yacoby Journal of High Energy Physics 2015 (3), 1-55, 2015 | 151 | 2015 |
| Scaling llm test-time compute optimally can be more effective than scaling model parameters C Snell, J Lee, K Xu, A Kumar arXiv preprint arXiv:2408.03314, 2024 | 65* | 2024 |
| Beyond human data: Scaling self-training for problem-solving with language models A Singh, JD Co-Reyes, R Agarwal, A Anand, P Patil, X Garcia, PJ Liu, ... arXiv preprint arXiv:2312.06585, 2023 | 63 | 2023 |
| On the infinite width limit of neural networks with a standard parameterization J Sohl-Dickstein, R Novak, SS Schoenholz, J Lee arXiv preprint arXiv:2001.07301, 2020 | 58 | 2020 |
| Small-scale proxies for large-scale transformer training instabilities M Wortsman, PJ Liu, L Xiao, K Everett, A Alemi, B Adlam, JD Co-Reyes, ... International Conference on Learning Representations (ICLR), Oral, 2024 | 41 | 2024 |
| Algebra of Majorana doubling J Lee, F Wilczek Physical Review Letters 111 (22), 226402, 2013 | 37 | 2013 |
| Towards NNGP-guided Neural Architecture Search DS Park*, J Lee*, D Peng, Y Cao, J Sohl-Dickstein arXiv preprint arXiv:2011.06006, 2020 | 34 | 2020 |
Jascha Sohl-DicksteinAnthropicVerified email at anthropic.com
