On Universality Classes of Equivariant Networks

NeurIPSSpotlight2025

Authors
Marco Pacini, Gabriele Santin, Bruno Lepri, Shubhendu Trivedi
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Equivariant neural networks provide a principled framework for incorporating symmetry into learning architectures and have been extensively analyzed through the lens of their *separation power*, that…

Opening excerpt from the authors’ abstract. source

Read the paper

← All NeurIPS 2025 Spotlight papers · Browse the whole archive