| Signal propagation in transformers: Theoretical perspectives and the role of rank collapse L Noci, S Anagnostidis, L Biggio, A Orvieto, SP Singh, A Lucchi Advances in Neural Information Processing Systems 35, 27198-27211, 2022 | 33 | 2022 |
| Adversarial learning for debiasing knowledge graph embeddings M Arduini, L Noci, F Pirovano, C Zhang, YR Shrestha, B Paudel arXiv preprint arXiv:2006.16309, 2020 | 33 | 2020 |
| Precise characterization of the prior predictive distribution of deep ReLU networks L Noci, G Bachmann, K Roth, S Nowozin, T Hofmann Advances in Neural Information Processing Systems 34, 20851-20862, 2021 | 28 | 2021 |
| Disentangling the roles of curation, data-augmentation and the prior in the cold posterior effect L Noci, K Roth, G Bachmann, S Nowozin, T Hofmann Advances in neural information processing systems 34, 12738-12748, 2021 | 15 | 2021 |
| Dynamic context pruning for efficient and interpretable autoregressive transformers S Anagnostidis, D Pavllo, L Biggio, L Noci, A Lucchi, T Hofmann Advances in Neural Information Processing Systems 36, 2024 | 14 | 2024 |
| Achieving a better stability-plasticity trade-off via auxiliary networks in continual learning S Kim, L Noci, A Orvieto, T Hofmann Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023 | 14 | 2023 |
| The shaped transformer: Attention models in the infinite depth-and-width limit L Noci, C Li, M Li, B He, T Hofmann, CJ Maddison, D Roy Advances in Neural Information Processing Systems 36, 2024 | 10 | 2024 |
| The curious case of benign memorization S Anagnostidis, G Bachmann, L Noci, T Hofmann arXiv preprint arXiv:2210.14019, 2022 | 5 | 2022 |
| How tempering fixes data augmentation in bayesian neural networks G Bachmann, L Noci, T Hofmann arXiv preprint arXiv:2205.13900, 2022 | 5 | 2022 |
| Depthwise hyperparameter transfer in residual networks: Dynamics and scaling limit B Bordelon, L Noci, MB Li, B Hanin, C Pehlevan arXiv preprint arXiv:2309.16620, 2023 | 4 | 2023 |
| Why do Learning Rates Transfer? Reconciling Optimization and Scaling Limits for Deep Learning L Noci, A Meterez, T Hofmann, A Orvieto arXiv preprint arXiv:2402.17457, 2024 | | 2024 |
| How Good is a Single Basin? K Lion, L Noci, T Hofmann, G Bachmann arXiv preprint arXiv:2402.03187, 2024 | | 2024 |
| Disentangling Linear Mode Connectivity GS Altıntaş, G Bachmann, L Noci, T Hofmann UniReps: the First Workshop on Unifying Representations in Neural Models, 2023 | | 2023 |
Thomas HofmannProfessor of Computer Science, ETH ZurichVerified email at inf.ethz.ch
