AI News HubLIVE
Original source2 min read

Singular Learning and Occam's Razor in Deep Monomial Networks

A new paper applies singular learning theory to deep monomial networks, showing that critical points correspond to subnetworks, providing a mathematical explanation for neural networks' implicit bias towards simpler functions.

SourcearXiv Machine LearningAuthor: Kathl\'en Kohn, Giovanni Luca Marchetti, Farhan Shabir, Vahid Shahverdi, Weisheng Wang

[2606.28464] Singular Learning and Occam's Razor in Deep Monomial Networks

[Submitted on 26 Jun 2026]

Title:Singular Learning and Occam's Razor in Deep Monomial Networks

View a PDF of the paper titled Singular Learning and Occam's Razor in Deep Monomial Networks, by Kathl\'en Kohn and 4 other authors

View PDF HTML (experimental)

Abstract:In the optimization of neural networks, gradient dynamics are influenced by critical points that arise from the model's architecture. These critical points occur where the Jacobian of the model's parametrization is rank-deficient, and are the most pronounced singularities studied in Singular Learning Theory. We investigate such points in deep fully-connected networks with monomial activations via tools from polynomial algebra such as Mason's Theorem. We show that, for sufficiently large activation degree, criticality occurs precisely at subnetworks, i.e., at parameter configurations where some neurons are inactive or redundant. This offers a mathematical perspective on the implicit bias in deep neural networks, explaining the tendency of these models to converge toward simpler functions.

Subjects:

Machine Learning (cs.LG)

Cite as: arXiv:2606.28464 [cs.LG]

(or arXiv:2606.28464v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2606.28464

arXiv-issued DOI via DataCite

Submission history

From: Giovanni Luca Marchetti [view email] [v1] Fri, 26 Jun 2026 13:40:14 UTC (34 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Singular Learning and Occam's Razor in Deep Monomial Networks, by Kathl\'en Kohn and 4 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-06

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

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.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)