English

Computational complexity of learning algebraic varieties

Algebraic Geometry 2020-10-19 v2 Machine Learning

Abstract

We analyze the complexity of fitting a variety, coming from a class of varieties, to a configuration of points in Cn\Bbb C^n. The complexity measure, called the algebraic complexity, computes the Euclidean Distance Degree (EDdegree) of a certain variety called the hypothesis variety as the number of points in the configuration increases. For the problem of fitting an (n1)(n-1)-sphere to a configuration of mm points in Cn\Bbb C^n, we give a closed formula of the algebraic complexity of the hypothesis variety as mm grows for the case of n=1n=1. For the case n>1n>1 we conjecture a generalization of this formula supported by numerical experiments.

Keywords

Cite

@article{arxiv.1910.03305,
  title  = {Computational complexity of learning algebraic varieties},
  author = {Oliver Gäfvert},
  journal= {arXiv preprint arXiv:1910.03305},
  year   = {2020}
}
R2 v1 2026-06-23T11:37:25.371Z