Any-dimensional equivariant neural networks

arXiv:2306.06327v2 Announce Type: replace
Abstract: Traditional supervised learning aims to learn an unknown mapping by fitting a function to a set of input-output pairs with a fixed dimension. The fitted function is then defined on inputs of the same dimension. However, in many settings, the unknown mapping takes inputs in any dimension; examples include graph parameters defined on graphs of any size and physics quantities defined on an arbitrary number of particles. We leverage a newly-discovered phenomenon in algebraic topology, …

abstract arxiv cs.lg examples function graph however input-output inputs learn mapping math.rt networks neural networks parameters set stat.ml supervised learning the unknown type