math.AGcs.LG

Linear Independence of Polynomial Compositions with Bounded Input Degree

📅 👥 2 authors arXiv:2610.20825v1

Authors

Abstract

We prove the weak composition-independence conjectures of Kohn, Marchetti, Massarenti and Mella. The proof uses deformations of rational curves and a single kernel of the linearized equation. Riemann-Roch gives a contradiction from tangent fields with controlled poles. By settling these conjectures, we prove that a neural network with a general polynomial activation function of sufficiently large degree is identifiable.

Paper Information

arXiv ID:
2610.20825v1
Published:

Related Categories

math.AGcs.LG