[2608.08003] The Spectral Neuron

Skip to main content

Search arXiv

Press Enter to search · Advanced search

-->

Statistics > Machine Learning

arXiv:2608.08003 (stat)

[Submitted on 8 Aug 2026 (v1), last revised 16 Aug 2026 (this version, v2)]

Title:The Spectral Neuron

Authors:Alex Shtoff<br>View a PDF of the paper titled The Spectral Neuron, by Alex Shtoff

View PDF<br>HTML (experimental)

Abstract:As machine learned models increase in complexity and expressive power, features of simpler models, such as intrinsic coefficient transparency and control over the shape of the modeled function are lost. On the one edge of the spectrum we have simple linear models that possess coefficient transparency, but have a limited expressive power. On the other edge we have neural networks, that have expressive power that improves with scaling, but are mostly opaque. In this work we develop the \emph{spectral neuron} concept: a scalar model given by $f(x)=\lambda_k (A_0 + A_1 x + ... + A_n x_n)$, with learned real symmetric matrices $A_0, ..., A_n$. The input enters the model through an affine matrix function, but the prediction is obtained by reading one of its eigenvalues. Thus, the model is nonlinear, but the source of nonlinearity is still mathematically explicit. This gives us a useful middle ground: the model can become more expressive as the matrix dimension grows, while retaining coefficient transparency through the learned matrices. For example, extremal eigenvalues yield convex or concave functions, semidefinite constraints on the coefficient matrices impose monotonicity, and the associated eigenspaces characterize local feature influence. We study coefficient transparency, feature-influence bounds, and shape-control properties of this model family, and then test whether it can be learned and scaled in practice. We develop a systematic study of this model family, bringing together spectral results from several mathematical literatures to characterize its expressivity, coefficient transparency, feature influence, and shape-control properties. Code available at this https URL.

Subjects:

Machine Learning (stat.ML); Machine Learning (cs.LG)

Cite as:<br>arXiv:2608.08003 [stat.ML]

(or<br>arXiv:2608.08003v2 [stat.ML] for this version)

https://doi.org/10.48550/arXiv.2608.08003

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Alex Shtoff [view email]<br>[v1]<br>Sat, 8 Aug 2026 08:31:26 UTC (4,699 KB)

[v2]<br>Sun, 16 Aug 2026 04:42:28 UTC (4,701 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled The Spectral Neuron, by Alex Shtoff<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

stat.ML

next >

new<br>recent<br>| 2026-08

Change to browse by:

cs<br>cs.LG<br>stat

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

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?)

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? |<br>Disable MathJax (What is MathJax?)

Major funding support from