The Spectral Neuron

• URL: http://arxiv.org/abs/2608.08003v2
• Date: Sun, 16 Aug 2026 04:42:28 GMT
• Title: The Spectral Neuron
• Abstract summary: As machine learned models increase in complexity and expressive power, features of simpler models are lost.<n>We develop the emphspectral neuron concept: a scalar model with learned real symmetric matrices.<n>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.
• Score: 0.7163391346004578
• License: http://creativecommons.org/licenses/by/4.0/
• 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 $f(x)=λ_k (A_0 + A_1 x + ... + A_n x_n)$, 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 https://github.com/alexshtf/spectral_neuron_paper.

Related papers

• Polyconvex Physics-Augmented Neural Network Constitutive Models in Principal Stretches [0.0]
  We show that a convex function can be described with a second-order and symmetric function.<n>The ability of the model to capture arbitrary materials is demonstrated using synthetic and experimental data.
  arXiv  Detail & Related papers  (2025-03-01T17:55:09Z)
• Low-Rank Matrix Factorizations with Volume-based Constraints and Regularizations [2.6687460222685226]
  This thesis focuses on volume-based constraints and regularizations designed to enhance interpretability and uniqueness.<n>Motivated by applications such as blind source separation and missing data imputation, this thesis also proposes efficient algorithms.
  arXiv  Detail & Related papers  (2024-12-09T10:58:23Z)
• Optimal Matrix-Mimetic Tensor Algebras via Variable Projection [0.0]
  Matrix mimeticity arises from interpreting tensors as operators that can be multiplied, factorized, and analyzed analogous to matrices. We learn optimal linear mappings and corresponding tensor representations without relying on prior knowledge of the data. We provide original theory of uniqueness of the transformation and convergence analysis of our variable-projection-based algorithm.
  arXiv  Detail & Related papers  (2024-06-11T04:52:23Z)
• Scaling and renormalization in high-dimensional regression [72.59731158970894]
  We present a unifying perspective on recent results on ridge regression.<n>We use the basic tools of random matrix theory and free probability, aimed at readers with backgrounds in physics and deep learning.<n>Our results extend and provide a unifying perspective on earlier models of scaling laws.
  arXiv  Detail & Related papers  (2024-05-01T15:59:00Z)
• On the Origins of Linear Representations in Large Language Models [51.88404605700344]
  We introduce a simple latent variable model to formalize the concept dynamics of the next token prediction. Experiments show that linear representations emerge when learning from data matching the latent variable model. We additionally confirm some predictions of the theory using the LLaMA-2 large language model.
  arXiv  Detail & Related papers  (2024-03-06T17:17:36Z)
• Quantized Fourier and Polynomial Features for more Expressive Tensor Network Models [9.18287948559108]
  We exploit the tensor structure present in the features by constraining the model weights to be an underparametrized tensor network. We show that, for the same number of model parameters, the resulting quantized models have a higher bound on the VC-dimension as opposed to their non-quantized counterparts.
  arXiv  Detail & Related papers  (2023-09-11T13:18:19Z)
• The Contextual Lasso: Sparse Linear Models via Deep Neural Networks [5.607237982617641]
  We develop a new statistical estimator that fits a sparse linear model to the explanatory features such that the sparsity pattern and coefficients vary as a function of the contextual features. An extensive suite of experiments on real and synthetic data suggests that the learned models, which remain highly transparent, can be sparser than the regular lasso.
  arXiv  Detail & Related papers  (2023-02-02T05:00:29Z)
• A simple probabilistic neural network for machine understanding [0.0]
  We discuss probabilistic neural networks with a fixed internal representation as models for machine understanding. We derive the internal representation by requiring that it satisfies the principles of maximal relevance and of maximal ignorance about how different features are combined. We argue that learning machines with this architecture enjoy a number of interesting properties, like the continuity of the representation with respect to changes in parameters and data.
  arXiv  Detail & Related papers  (2022-10-24T13:00:15Z)
• Graph Polynomial Convolution Models for Node Classification of Non-Homophilous Graphs [52.52570805621925]
  We investigate efficient learning from higher-order graph convolution and learning directly from adjacency matrix for node classification. We show that the resulting model lead to new graphs and residual scaling parameter. We demonstrate that the proposed methods obtain improved accuracy for node-classification of non-homophilous parameters.
  arXiv  Detail & Related papers  (2022-09-12T04:46:55Z)
• Curvature-informed multi-task learning for graph networks [56.155331323304]
  State-of-the-art graph neural networks attempt to predict multiple properties simultaneously. We investigate a potential explanation for this phenomenon: the curvature of each property's loss surface significantly varies, leading to inefficient learning.
  arXiv  Detail & Related papers  (2022-08-02T18:18:41Z)
• Hessian Eigenspectra of More Realistic Nonlinear Models [73.31363313577941]
  We make a emphprecise characterization of the Hessian eigenspectra for a broad family of nonlinear models. Our analysis takes a step forward to identify the origin of many striking features observed in more complex machine learning models.
  arXiv  Detail & Related papers  (2021-03-02T06:59:52Z)
• Non-parametric Models for Non-negative Functions [48.7576911714538]
  We provide the first model for non-negative functions from the same good linear models. We prove that it admits a representer theorem and provide an efficient dual formulation for convex problems.
  arXiv  Detail & Related papers  (2020-07-08T07:17:28Z)
• Spectral Learning on Matrices and Tensors [74.88243719463053]
  We show that tensor decomposition can pick up latent effects that are missed by matrix methods. We also outline computational techniques to design efficient tensor decomposition methods.
  arXiv  Detail & Related papers  (2020-04-16T22:53:00Z)
• Learning Bijective Feature Maps for Linear ICA [73.85904548374575]
  We show that existing probabilistic deep generative models (DGMs) which are tailor-made for image data, underperform on non-linear ICA tasks. To address this, we propose a DGM which combines bijective feature maps with a linear ICA model to learn interpretable latent structures for high-dimensional data. We create models that converge quickly, are easy to train, and achieve better unsupervised latent factor discovery than flow-based models, linear ICA, and Variational Autoencoders on images.
  arXiv  Detail & Related papers  (2020-02-18T17:58:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.