Publications

  1. “Understanding and Minimising Outlier Features in Neural Network Training.” Bobby He, Lorenzo Noci, Daniele Paliotta, Imanol Schlag, Thomas Hofmann. Advances in Neural Information Processing Systems (NeurIPS), 2024. arXiv

  2. “Super Consistency of Neural Network Landscapes and Learning Rate Transfer.” Lorenzo Noci†, Alex Meterez†, Thomas Hofmann, Antonio Orvieto. Advances in Neural Information Processing Systems (NeurIPS), 2024. arXiv

  3. “Exploring the Limits of Feature Learning in Continual Learning.” Jacopo Graldi†, Giulia Lanzillotta, Lorenzo Noci, Benjamin Grewe, Thomas Hofmann. Continual FoMo Workshop at NeurIPS, 2024. OpenReview

  4. “Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit.” Blake Bordelon†, Lorenzo Noci†, Mufan Bill Li, Boris Hanin, Cengiz Pehlevan. International Conference on Learning Representations (ICLR), 2024. arXiv

  5. “How Good is a Single Basin?” Kai Lion, Lorenzo Noci, Thomas Hofmann, Gregor Bachmann. Artificial Intelligence and Statistics (AISTATS), 2024. arXiv

  6. “Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers.” (Spotlight) Sotiris Anagnostidis, Dario Pavllo, Luca Biggio, Lorenzo Noci, Aurelien Lucchi, Thomas Hofmann. Advances in Neural Information Processing Systems (NeurIPS), 2023. arXiv

  7. “The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit.” Lorenzo Noci†, Chuning Li†, Mufan Bill Li†, Bobby He, Thomas Hofmann, Chris Maddison, Daniel M. Roy. Advances in Neural Information Processing Systems (NeurIPS), 2023. arXiv

  8. “Disentangling Linear Mode-Connectivity.” Gül Sena Altıntaş, Gregor Bachmann, Lorenzo Noci, Thomas Hofmann. UniReps Workshop at NeurIPS, 2023. arXiv

  9. “Achieving a Better Stability-Plasticity Trade-off via Auxiliary Networks in Continual Learning.” Sanghwan Kim†, Lorenzo Noci, Antonio Orvieto, and Thomas Hofmann. IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023. arXiv

  10. “The Curious Case of Benign Memorization.” Sotiris Anagnostidis†, Gregor Bachmann†, Lorenzo Noci†, and Thomas Hofmann. International Conference on Learning Representations (ICLR), 2023. arXiv

  11. “Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse.” Lorenzo Noci†, Sotiris Anagnostidis†, Luca Biggio†, Antonio Orvieto†, Sidak Pal Singh†, and Aurelien Lucchi. Advances in Neural Information Processing Systems (NeurIPS), 2022. arXiv

  12. “How Tempering Fixes Data Augmentation in Bayesian Neural Networks.” (Oral) Gregor Bachmann†, Lorenzo Noci†, and Thomas Hofmann. International Conference on Machine Learning, pages 1244–1260, PMLR, 2022. arXiv

  13. “Precise Characterization of the Prior Predictive Distribution of Deep ReLU Networks.” (Spotlight) Lorenzo Noci†, Gregor Bachmann†, Kevin Roth†, Sebastian Nowozin, and Thomas Hofmann. Advances in Neural Information Processing Systems, 34, 2021. arXiv

  14. “Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect.” Lorenzo Noci†, Kevin Roth†, Gregor Bachmann†, Sebastian Nowozin, and Thomas Hofmann. Advances in Neural Information Processing Systems (NeurIPS), 34, 2021. arXiv

  15. “Adversarial Learning for Debiasing Knowledge Graph Embeddings.” Mario Arduini†, Lorenzo Noci†, Federico Pirovano†, Ce Zhang, Yash Raj Shrestha, and Bibek Paudel. Workshop on Mining and Learning with Graphs at KDD. arXiv