| High-Performance Large-Scale Image Recognition Without Normalization A Brock, S De, SL Smith, K Simonyan International Conference on Machine Learning, 2021 | 601 | 2021 |
| Gemma: Open Models Based on Gemini Research and Technology G Team, T Mesnard, C Hardin, R Dadashi, S Bhupatiraju, S Pathak, ... arXiv preprint arXiv:2403.08295, 2024 | 425 | 2024 |
| Adversarial robustness through local linearization C Qin, J Martens, S Gowal, D Krishnan, K Dvijotham, A Fawzi, S De, ... Advances in Neural Information Processing Systems, 13847-13856, 2019 | 345 | 2019 |
| Training quantized nets: A deeper understanding H Li*, S De*, Z Xu, C Studer, H Samet, T Goldstein Advances in Neural Information Processing Systems, 5813-5823, 2017 | 245 | 2017 |
| On the Origin of Implicit Regularization in Stochastic Gradient Descent SL Smith, B Dherin, DGT Barrett, S De International Conference on Learning Representations, 2021 | 200 | 2021 |
| Unlocking High-Accuracy Differentially Private Image Classification through Scale S De, L Berrada, J Hayes, SL Smith, B Balle ICML Workshop on Theory and Practice of Differential Privacy, 2022 | 191* | 2022 |
| Resurrecting Recurrent Neural Networks for Long Sequences A Orvieto, SL Smith, A Gu, A Fernando, C Gulcehre, R Pascanu, S De arXiv preprint arXiv:2303.06349, 2023 | 189 | 2023 |
| Batch normalization biases residual blocks towards the identity function in deep networks S De, S Smith Advances in Neural Information Processing Systems 33, 2020 | 172* | 2020 |
| The loosening of American culture over 200 years is associated with a creativity–order trade-off JC Jackson, M Gelfand, S De, A Fox Nature human behaviour 3 (3), 244-250, 2019 | 166* | 2019 |
| Convergence guarantees for RMSProp and ADAM in non-convex optimization and an empirical comparison to Nesterov acceleration S De, A Mukherjee, E Ullah ICML Workshop on Modern Trends in Nonconvex Optimization for Machine Learning, 2018 | 157* | 2018 |
| Automated inference with adaptive batches S De, A Yadav, D Jacobs, T Goldstein Artificial Intelligence and Statistics, 1504-1513, 2017 | 154* | 2017 |
| Characterizing signal propagation to close the performance gap in unnormalized ResNets A Brock, S De, SL Smith International Conference on Learning Representations, 2021 | 134 | 2021 |
| BYOL works even without batch statistics PH Richemond, JB Grill, F Altché, C Tallec, F Strub, A Brock, S Smith, ... NeurIPS Workshop on Self-Supervised Learning: Theory and Practice, 2020 | 130* | 2020 |
| On the Generalization Benefit of Noise in Stochastic Gradient Descent S Smith, E Elsen, S De International Conference on Machine Learning, 9058-9067, 2020 | 122* | 2020 |
| The impact of neural network overparameterization on gradient confusion and stochastic gradient descent KA Sankararaman*, S De*, Z Xu, WR Huang, T Goldstein International Conference on Machine Learning, 8469-8479, 2020 | 113 | 2020 |
| Understanding norm change: An evolutionary game-theoretic approach S De, DS Nau, MJ Gelfand Proceedings of the 16th Conference on Autonomous Agents and MultiAgent …, 2017 | 76* | 2017 |
| Layer-specific adaptive learning rates for deep networks B Singh, S De, Y Zhang, T Goldstein, G Taylor 2015 IEEE 14th International Conference on Machine Learning and Applications …, 2015 | 69 | 2015 |
| Efficient distributed SGD with variance reduction S De, T Goldstein 2016 IEEE International Conference on Data Mining (ICDM), 2016 | 55* | 2016 |
| Differentially Private Diffusion Models Generate Useful Synthetic Images S Ghalebikesabi, L Berrada, S Gowal, I Ktena, R Stanforth, J Hayes, S De, ... arXiv preprint arXiv:2302.13861, 2023 | 53 | 2023 |
| Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models S De, SL Smith, A Fernando, A Botev, G Cristian-Muraru, A Gu, R Haroun, ... arXiv preprint arXiv:2402.19427, 2024 | 50* | 2024 |
Samuel L. SmithDeepMindVerified email at google.com
