publications

Check Google Scholar for the most updated list. * denotes co-first authorship.

2023

  1. Task arithmetic in the tangent space: Improved editing of pre-trained models
    Guillermo Ortiz-Jimenez*, Alessandro Favero*, and Pascal Frossard
    arXiv preprint, 2023
  2. What can be learnt with wide convolutional neural networks?
    Francesco Cagnetta*, Alessandro Favero*, and Matthieu Wyart
    ICML, Proceedings of Machine Learning Research, 2023

2021

  1. Locality defeats the curse of dimensionality in convolutional teacher-student scenarios
    Alessandro Favero*, Francesco Cagnetta*, and Matthieu Wyart
    Advances in Neural Information Processing Systems, 2021
    Journal of Statistical Mechanics, Theory and Experiment, 2022
  2. Relative stability toward diffeomorphisms indicates performance in deep nets
    Leonardo Petrini, Alessandro Favero, Mario Geiger, and Matthieu Wyart
    Advances in Neural Information Processing Systems, 2021
    Journal of Statistical Mechanics, Theory and Experiment, 2022

2020

  1. Spectral analysis of infinitely wide convolutional neural networks
    Alessandro Favero
    Master’s Thesis, Sorbonne Université and Politecnico di Torino, 2020