Symmetry in Neural Network Parameter Spaces

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Bo, Walters, Robin, Yu, Rose
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911312023388160
author Zhao, Bo
Walters, Robin
Yu, Rose
author_facet Zhao, Bo
Walters, Robin
Yu, Rose
contents Modern deep learning models are highly overparameterized, resulting in large sets of parameter configurations that yield the same outputs. A significant portion of this redundancy is explained by symmetries in the parameter space--transformations that leave the network function unchanged. These symmetries shape the loss landscape and constrain learning dynamics, offering a new lens for understanding optimization, generalization, and model complexity that complements existing theory of deep learning. This survey provides an overview of parameter space symmetry. We summarize existing literature, uncover connections between symmetry and learning theory, and identify gaps and opportunities in this emerging field.
format Preprint
id arxiv_https___arxiv_org_abs_2506_13018
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Symmetry in Neural Network Parameter Spaces
Zhao, Bo
Walters, Robin
Yu, Rose
Machine Learning
Artificial Intelligence
Modern deep learning models are highly overparameterized, resulting in large sets of parameter configurations that yield the same outputs. A significant portion of this redundancy is explained by symmetries in the parameter space--transformations that leave the network function unchanged. These symmetries shape the loss landscape and constrain learning dynamics, offering a new lens for understanding optimization, generalization, and model complexity that complements existing theory of deep learning. This survey provides an overview of parameter space symmetry. We summarize existing literature, uncover connections between symmetry and learning theory, and identify gaps and opportunities in this emerging field.
title Symmetry in Neural Network Parameter Spaces
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2506.13018