Pre-prints

2025

• Ringel Z., Rubin N., Mor E., Helias M., Seroussi I. (2025 ) Applications of Statistical Field Theory in Deep Learning. arXiv: 10.48550/arxiv.2502.18553
  
  
• Rubin N., Fischer K., Lindner J., Dahmen D., Seroussi I., Ringel Z., Krämer M., Helias M. (2025) From Kernels to Features: A Multi-scale Adaptive Theory of Feature Learning. arXiv: 10.48550/arXiv.2502.03210
  
  

2024

• Epping B., René A., Helias M., Schaub MT. (2014) Graph Neural Networks Do Not Always Oversmooth. arXiv: 10.48550/arXiv.2406.02269
  
  
• Ness TV., Tetzlaff T., Einevoll GT., Dahmen D. (2024) On the validity of electric brain signal predictions based on population firing rates. bioRxiv: 10.1101/2024.07.10.602833
  
  

2023

• Fischer K., David D., Helias M. (2023) Optimal signal propagation in ResNets through residual scaling. Submitted to NeurIPS 2023. ArXiv: https://arxiv.org/abs/2305.07715
  

2022

• Keup C., Helias M. (2022) Origami in N dimensions: How feed-forward networks manufacture linear separability.
  ArXiv: 10.48550/arXiv.2203.11355
  
  
• Stubenrauch J., Keup C., Kurth AC., Helias M., van Meegen A. (2022) Phase Space Analysis of Chaotic Neural Networks.
  ArXiv: 10.48550/arXiv.2210.07877