Newshot

Defining equations for two-block shallow ReLU pattern varieties

Summary

arXiv:2611.23846v1 Announce Type: cross Abstract: We give a complete algebraic characterization of two-block shallow ReLU pattern varieties. We show that the determinantal equations arising from rank constraints imposed by the activation patterns generate the defining ideals, thereby proving a conjecture of Alexandr-Mont\'ufar. The set-theoretic proof uses a characterization of orbit closures of matrix pencils in terms of the Kronecker canonical form.

Original text(via arXiv stat.ML)

Mathematics > Algebraic Geometry

Title:Defining equations for two-block shallow ReLU pattern varieties

Abstract:We give a complete algebraic characterization of two-block shallow ReLU pattern varieties. We show that the determinantal equations arising from rank constraints imposed by the activation patterns generate the defining ideals, thereby proving a conjecture of Alexandr-Montúfar. The set-theoretic proof uses a characterization of orbit closures of matrix pencils in terms of the Kronecker canonical form.
Comments:22 pages
Subjects:Algebraic Geometry (math.AG) ; Machine Learning (stat.ML)
Cite as:arXiv:2611.23846 [math.AG]
(or arXiv:2611.23846v1 [math.AG] for this version)
https://doi.org/10.48550/arXiv.2611.23846 arXiv-issued DOI via DataCite (pending registration)

Submission history

Access Paper:

  • HTML (experimental)

Current browse context:

References & Citations

  • Google Scholar
  • Semantic Scholar

BibTeX formatted citation

Bookmark

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

The text above was extracted automatically from the source page and may miss images, tables or code blocks. The original is authoritative.

Published by arXiv stat.ML
This site only summarises and aggregates; copyright stays with the original author. Headlines and summaries follow the source — where they differ, the original wins.
Read the original ↗