| Online normalization for training neural networks V Chiley, I Sharapov, A Kosson, U Koster, R Reece, ... Advances in Neural Information Processing Systems 32, 2019 | 51 | 2019 |
| Pipelined backpropagation at scale: training large models without batches A Kosson, V Chiley, A Venigalla, J Hestness, U Koster Proceedings of Machine Learning and Systems 3, 479-501, 2021 | 26 | 2021 |
| Stance detection for fake news identification D Mrowca, E Wang, A Kosson Eliaswang. Com, 2017 | 22 | 2017 |
| Deep action conditional neural network for frame prediction in Atari games E Wang, A Kosson, T Mu Technical report, 2017 | 17 | 2017 |
| Adaptive Braking for Mitigating Gradient Delay A Venigalla, A Kosson, V Chiley, U Köster Beyond First Order Methods in ML Systems workshop at the 37th International …, 2020 | 2 | 2020 |
| Ghost Noise for Regularizing Deep Neural Networks A Kosson, D Fan, M Jaggi AAAI 2024, 2023 | 1 | 2023 |
| Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks A Kosson, B Messmer, M Jaggi NeurIPS 2023 Workshop on Mathematics of Modern Machine Learning, 2023 | | 2023 |
| Understanding the Role of Noisy Statistics in the Regularization Effect of Batch Normalization A Kosson, D Fan, M Jaggi NeurIPS 2023 Workshop on Mathematics of Modern Machine Learning, 2023 | | 2023 |
| Multiplication-Free Transformer Training via Piecewise Affine Operations A Kosson, M Jaggi NeurIPS 2023 - Advances in Neural Information Processing Systems, 2023 | | 2023 |
| Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks A Kosson, B Messmer, M Jaggi arXiv:2305.17212, 2023 | | 2023 |
Urs KösterCerebrasVerified email at cerebras.net
