Lemma 3 — Top boundary injectivity
OpenTwoReLULayers.DepthCollapse.Supplement.top_differential_injectivemachine-learningp2o-batch-stoc27sp2o-gran-per-chapterp2o-plan-paperp2o-v1polytope-geometryrelu-networks
Let . In the rational oriented polytope quotient , the top boundary is injective:
The assertion applies to every class in the geometric quotient, including classes not known to lie in the paramid span. It identifies a top-dimensional class by its boundary.
Differences from the source:
- encoding: Rational polytopes in oriented subspaces, with Minkowski differences modulo translations and lower-dimensional terms → Finite rational vertex and ordered-frame presentation of the same geometric quotient; reason: The presentation imposes exactly those geometric relations; facet boundaries are evaluated on a chosen representative, with no extra hypothesis
- encoding: n ≥ 2 → n = m+2, m : ℕ; reason: Equivalent enumeration of every permitted natural dimension or degree; avoids dependent transports from natural subtraction
Preamble
import Definitions.Def_TwoReLULayers_DepthCollapse_Supplement_Realization
Formal statement
namespace TwoReLULayers.DepthCollapse.Supplement
/-- Lemma 3, p.11. The parameter n+2 ranges over every ambient dimension ≥2. -/
theorem top_differential_injective (n : ℕ) :
Function.Injective (dP (n + 2) (n + 2)) := by sorry
end TwoReLULayers.DepthCollapse.Supplement
Source
Kilian Rueß, Florestan Brunck, Christoph Hertrich, Jack Stade, Amir Yehudayoff, Two ReLU layers is all you need, STOC 2027 submission #980 (October 2026). Use this pinned PDF and its own labels; no arXiv version is asserted. p. 11, Lemma 3.