mlsanityData to 14 Oct 2026

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

arXiv 2610.04256 ↗First posted 3 Oct 2026cs.LG cs.CCcited by 0

Not on the map. Why?

Abstract (arXiv)

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 17 and 41, zero biases, and rational weights.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 5 of its 5 references that are in the map. First posted on arXiv 3 Oct 2026.

Builds on

5 of 5 references.

References · 5

  1. 2016Understanding Deep Neural Networks with Rectified Linear Unitscited by 257
  2. 2021Towards Lower Bounds on the Depth of ReLU Neural Networkscited by 56
  3. 2025Better Neural Network Expressivity: Subdividing the Simplexcited by 12
  4. 2026Shallower ReLU Network Representations via Exact Linear Algebracited by 3
  5. 2026Representing MAX functions using two-hidden-layer ReLU networkscited by 1

Built on by

Not cited yet.