English

Training Neural Networks is $\exists\mathbb R$-complete

Computational Complexity 2021-11-22 v2 Artificial Intelligence Data Structures and Algorithms Machine Learning Neural and Evolutionary Computing

Abstract

Given a neural network, training data, and a threshold, it was known that it is NP-hard to find weights for the neural network such that the total error is below the threshold. We determine the algorithmic complexity of this fundamental problem precisely, by showing that it is R\exists\mathbb R-complete. This means that the problem is equivalent, up to polynomial-time reductions, to deciding whether a system of polynomial equations and inequalities with integer coefficients and real unknowns has a solution. If, as widely expected, R\exists\mathbb R is strictly larger than NP, our work implies that the problem of training neural networks is not even in NP. Neural networks are usually trained using some variation of backpropagation. The result of this paper offers an explanation why techniques commonly used to solve big instances of NP-complete problems seem not to be of use for this task. Examples of such techniques are SAT solvers, IP solvers, local search, dynamic programming, to name a few general ones.

Keywords

Cite

@article{arxiv.2102.09798,
  title  = {Training Neural Networks is $\exists\mathbb R$-complete},
  author = {Mikkel Abrahamsen and Linda Kleist and Tillmann Miltzow},
  journal= {arXiv preprint arXiv:2102.09798},
  year   = {2021}
}

Comments

12 pages, 4 figures, accepted at NeurIPS 2021

R2 v1 2026-06-23T23:19:07.130Z