today local_bar

Marco Pacini

PhD student, Fondazione Bruno Kessler

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 6

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

On Universality Classes of Equivariant Networks

#3700 Spotlight · Marco Pacini, Gabriele Santin, Bruno Lepri, Shubhendu Trivedi

Equivariant neural networks can fail to approximate target functions even when they achieve maximal separation power.