English

Reachability Is NP-Complete Even for the Simplest Neural Networks

Computational Complexity 2022-03-16 v2 Machine Learning

Abstract

We investigate the complexity of the reachability problem for (deep) neural networks: does it compute valid output given some valid input? It was recently claimed that the problem is NP-complete for general neural networks and conjunctive input/output specifications. We repair some flaws in the original upper and lower bound proofs. We then show that NP-hardness already holds for restricted classes of simple specifications and neural networks with just one layer, as well as neural networks with minimal requirements on the occurring parameters.

Keywords

Cite

@article{arxiv.2108.13179,
  title  = {Reachability Is NP-Complete Even for the Simplest Neural Networks},
  author = {Marco Sälzer and Martin Lange},
  journal= {arXiv preprint arXiv:2108.13179},
  year   = {2022}
}