Marco Pacini

PhD Candidate at University of Trento & Fondazione Bruno Kessler

personal-pic.jpg

My research focuses on the fundamental principles of Geometric Deep Learning and Equivariant Machine Learning.

Some of my research interests include the constructive characterization of equivariant models, as well as their expressivity and approximation capabilities.

News

Feb 11, 2025 Our latest paper, “Separation Power of Equivariant Neural Networks,” has been accepted to ICLR 2025! ✨
Jun 14, 2024 New preprint of “Separation Power of Equivariant Neural Networks” is out on ArXiv now! 🎉
Jan 15, 2024 Our latest paper “A Characterization Theorem for Equivariant Networks with Point-wise Activations” has been accepted at ICLR 2024! 📘

Selected Publications

  1. ICLR
    twin-network.jpg
    Separation Power of Equivariant Neural Networks
    Marco Pacini, Xiaowen Dong, Bruno Lepri, and 1 more author
    2025
  2. ICLR
    equivariant.jpg
    A Characterization Theorem for Equivariant Networks with Point-wise Activations
    Marco Pacini, Xiaowen Dong, Bruno Lepri, and 1 more author
    International Conference on Learning Representations, 2024