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

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 $\exists \mathbb{R}$-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, $\exists \mathbb{R}$ 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.

arXiv comment12 pages, 4 figures, accepted at NeurIPS 2021

Cited by in corpus (6)

• The Computational Complexity of ReLU Network Training Parameterized by Data Dimensionality
• On Classifying Continuous Constraint Satisfaction Problems
• A Practical Algorithm with Performance Guarantees for the Art Gallery Problem
• Topological Art in Simple Galleries
• On the Stability Properties and the Optimization Landscape of Training Problems with Squared Loss for Neural Networks and General Nonlinear Conic Approximation Schemes
• Representing Matroids over the Reals is $\exists \mathbb{R}$-complete