English

Universal Equivariant Multilayer Perceptrons

Machine Learning 2020-06-26 v2 Neural and Evolutionary Computing Group Theory Machine Learning

Abstract

Group invariant and equivariant Multilayer Perceptrons (MLP), also known as Equivariant Networks, have achieved remarkable success in learning on a variety of data structures, such as sequences, images, sets, and graphs. Using tools from group theory, this paper proves the universality of a broad class of equivariant MLPs with a single hidden layer. In particular, it is shown that having a hidden layer on which the group acts regularly is sufficient for universal equivariance (invariance). A corollary is unconditional universality of equivariant MLPs for Abelian groups, such as CNNs with a single hidden layer. A second corollary is the universality of equivariant MLPs with a high-order hidden layer, where we give both group-agnostic bounds and means for calculating group-specific bounds on the order of hidden layer that guarantees universal equivariance (invariance).

Keywords

Cite

@article{arxiv.2002.02912,
  title  = {Universal Equivariant Multilayer Perceptrons},
  author = {Siamak Ravanbakhsh},
  journal= {arXiv preprint arXiv:2002.02912},
  year   = {2020}
}
R2 v1 2026-06-23T13:34:33.280Z