On the Architectural Complexity of Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cooper, Nicholas J., Meyer, François G., Roberts, Michael L., Zapata-Carratalá, Carlos, Chen, Lijun, Gurari, Danna
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914533406146560
author Cooper, Nicholas J.
Meyer, François G.
Roberts, Michael L.
Zapata-Carratalá, Carlos
Chen, Lijun
Gurari, Danna
author_facet Cooper, Nicholas J.
Meyer, François G.
Roberts, Michael L.
Zapata-Carratalá, Carlos
Chen, Lijun
Gurari, Danna
contents We introduce a unified theoretical framework for the rigorous analysis and systematic construction of deep neural networks (DNNs). This framework addresses a gap in existing theory by explicitly modeling the structure of tensor operations -- lower level information that is often abstracted. Our framework enables two novel objectives: (1) analysis of the evolution of architectural complexity over deep learning history, and (2) automatic construction of novel architectures based on new types of tensor operations. Our study of DNNs introduced over the past 40 years reveals a connection between groundbreaking architectures and increases in different types of architectural complexity. Moreover, we identify several large classes of higher complexity architectures that have not yet been explored. We then collect a dataset of 3,000+ higher complexity architectures, which we publicly release at: https://github.com/combinatoriallabs/ArchitecturalComplexity.
format Preprint
id arxiv_https___arxiv_org_abs_2605_04325
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle On the Architectural Complexity of Neural Networks
Cooper, Nicholas J.
Meyer, François G.
Roberts, Michael L.
Zapata-Carratalá, Carlos
Chen, Lijun
Gurari, Danna
Machine Learning
Discrete Mathematics
Combinatorics
We introduce a unified theoretical framework for the rigorous analysis and systematic construction of deep neural networks (DNNs). This framework addresses a gap in existing theory by explicitly modeling the structure of tensor operations -- lower level information that is often abstracted. Our framework enables two novel objectives: (1) analysis of the evolution of architectural complexity over deep learning history, and (2) automatic construction of novel architectures based on new types of tensor operations. Our study of DNNs introduced over the past 40 years reveals a connection between groundbreaking architectures and increases in different types of architectural complexity. Moreover, we identify several large classes of higher complexity architectures that have not yet been explored. We then collect a dataset of 3,000+ higher complexity architectures, which we publicly release at: https://github.com/combinatoriallabs/ArchitecturalComplexity.
title On the Architectural Complexity of Neural Networks
topic Machine Learning
Discrete Mathematics
Combinatorics
url https://arxiv.org/abs/2605.04325