The Alexander-Hirschowitz theorem for neurovarieties
Algebraic Geometry
2025-11-26 v1 Artificial Intelligence
Machine Learning
Commutative Algebra
Abstract
We study neurovarieties for polynomial neural networks and fully characterize when they attain the expected dimension in the single-output case. As consequences, we establish non-defectiveness and global identifiability for multi-output architectures.
Cite
@article{arxiv.2511.19703,
title = {The Alexander-Hirschowitz theorem for neurovarieties},
author = {A. Massarenti and M. Mella},
journal= {arXiv preprint arXiv:2511.19703},
year = {2025}
}
Comments
21 pages