About me

I am a PhD student in the Methods of Machine Learning group led by Prof. Philipp Hennig at the University of Tübingen. My research focuses on incorporating uncertainty quantification into deep learning methods for solving partial differential equations, with a particular interest in probabilistic numerics and neural operators.

Selected publications

Linearization Turns Neural Operators into Function-Valued Gaussian Processes

Emilia Magnani, Marvin Pförtner, Tobias Weber, Philipp Hennig

ICML (Spotlight), 2025

Paper Code

BibTeX

@InProceedings{pmlr-v267-magnani25a,
  title = {Linearization Turns Neural Operators into Function-Valued {G}aussian Processes},
  author = {Magnani, Emilia and Pf\"{o}rtner, Marvin and Weber, Tobias and Hennig, Philipp},
  booktitle = {Proceedings of the 42nd International Conference on Machine Learning},
  pages = {42421--42452},
  year = {2025},
  editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry},
  volume = {267},
  series = {Proceedings of Machine Learning Research},
  month = {13--19 Jul},
  publisher = {PMLR},
  url = {https://proceedings.mlr.press/v267/magnani25a.html},
}