English

Equivariant neural networks for recovery of Hadamard matrices

Machine Learning 2022-02-01 v1 Discrete Mathematics

Abstract

We propose a message passing neural network architecture designed to be equivariant to column and row permutations of a matrix. We illustrate its advantages over traditional architectures like multi-layer perceptrons (MLPs), convolutional neural networks (CNNs) and even Transformers, on the combinatorial optimization task of recovering a set of deleted entries of a Hadamard matrix. We argue that this is a powerful application of the principles of Geometric Deep Learning to fundamental mathematics, and a potential stepping stone toward more insights on the Hadamard conjecture using Machine Learning techniques.

Keywords

Cite

@article{arxiv.2201.13157,
  title  = {Equivariant neural networks for recovery of Hadamard matrices},
  author = {Augusto Peres and Eduardo Dias and Luís Sarmento and Hugo Penedones},
  journal= {arXiv preprint arXiv:2201.13157},
  year   = {2022}
}