cs.LGOct 3, 2026

A Hand-Checkable Proof That Two Hidden ReLU Layers Compute the Maximum of Six Numbers

Authors: Dimitrios Myrisiotis

Organizations: Great Bay University China

Abstract

Exactly computing the maximum function is a standard test case for studying depth in ReLU networks. Two hidden layers are known to suffice for up to twelve inputs through computer-assisted constructions. For six real inputs, we give an explicit hexagon identity whose local structure yields a self-contained analytical proof of this depth bound. The identity was found by computer-assisted search; we prove it through explicit cancellations that can be checked entirely by hand, without executing a verification program. The identity also yields an explicit network with hidden widths 1717 and 4141, zero biases, and rational weights.

Explore similar work

CardsList
  1. Shallower ReLU Network Representations via Exact Linear Algebra

    Jul 22, 2026Kilian Rueß, Gennadiy Averkov, Florestan Brunck +7Shallow Neural NetworksReLU Neural Networks

  2. Representing MAX functions using two-hidden-layer ReLU networks

    Aug 25, 2026Zhimao Wang, Amitabh BasuReLU Neural NetworksNeural Network Expressivity